Recently runtime-tested skills

This skill extracts transcripts from YouTube videos and generates summaries. It references external endpoints and uses shell commands, including `sudo`.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Use Caution

Current public label: Use Caution

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill scrapes data from X (Twitter) using the Xquik platform, including tweet searches, user profiles, and engagement metrics.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No obvious script files found; disconnected runtime evidence may remain shallow.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Use Caution

Current public label: Use Caution

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 3 low, 1 info

This skill integrates with the WhatsApp Business Cloud API to send messages, use templates, and automate customer service.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: High Risk

Current public label: High Risk

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill builds web artifacts by initializing a frontend repo, developing the artifact, and bundling the code into a single HTML file.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill is a vulnerability scanner. It uses credentials or secrets and includes shell-oriented behavior.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill appears to be a documentation-based guide for managing environment variables in Claude Code sessions. It mentions credentials and external endpoints.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No obvious script files found; disconnected runtime evidence may remain shallow.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 3 low, 1 info

This skill provides a design guide for web and mobile applications, including styles, color palettes, font pairings, UX guidelines, and chart types.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill is designed to be an advanced TypeScript expert. Driftloom found that it contains a destructive shell pattern and references an external URL.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill provides testing strategies for Temporal workflows using pytest. Driftloom found that the skill uses shell commands and makes network calls.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No obvious script files found; disconnected runtime evidence may remain shallow.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 3 low, 1 info

This skill integrates with the Telegram Bot API, offering features like bot setup, messaging, webhooks, and inline keyboards.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: High Risk

Current public label: High Risk

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill integrates with Stripe for payment processing, including checkout, subscriptions, webhooks, and refunds.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No obvious script files found; disconnected runtime evidence may remain shallow.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Trusted

Current public label: Trusted

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 3 low, 1 info

This skill generates images using Stability AI, offering text-to-image, image editing, and upscaling features.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill performs SSH security assessments, including enumeration, credential attacks, and exploitation. Driftloom found that the skill's source code is mostly documentation.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No obvious script files found; disconnected runtime evidence may remain shallow.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 3 low, 1 info

This skill analyzes the quality, security, and costs of other skills.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill helps with Shopify development tasks. It may reference external URLs and credentials.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill uses Shodan to find exposed services and vulnerable systems. It appears to be mostly documentation.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No obvious script files found; disconnected runtime evidence may remain shallow.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Use Caution

Current public label: Use Caution

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 3 low, 1 info

This skill provides frontend development patterns, performance optimization, and automation tools for React/Next.js applications.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill scaffolds Python project structures, including tooling, type hints, and testing setup. It generates project structures based on current best practices.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No obvious script files found; disconnected runtime evidence may remain shallow.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 3 low, 1 info

This skill can create, edit, and analyze.pptx files. It uses different tools and workflows for various tasks.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Use Caution

Current public label: Use Caution

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info

This skill uses Playwright to automate browser tasks. It can perform any automation task you request.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• Documented/runtime hint command did not behave like help/version output: npm run setup -- --help
• Documented/runtime hint command did not behave like help/version output: npm run install-all-browsers -- --help

Automated result: Use Caution

Current public label: Use Caution

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 medium, 3 low

This skill provides a command reference for penetration testing tools. It is designed to help with quick command lookup during security assessments.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No obvious script files found; disconnected runtime evidence may remain shallow.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Use Caution

Current public label: Use Caution

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 3 low, 1 info

This skill provides documentation for building a payments stack for Pakistani SaaS systems.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No obvious script files found; disconnected runtime evidence may remain shallow.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Trusted

Current public label: Trusted

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 3 low, 1 info

This skill provides documentation on Odoo backup strategies, including database and filestore backups, offsite storage, and restore procedures.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No obvious script files found; disconnected runtime evidence may remain shallow.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: Needs Review

Current public label: Needs Review

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 3 low, 1 info

This skill interacts with Google NotebookLM to answer questions based on your uploaded documents.

Source: Workspace import

Originally ingested from a local workspace copy.

Runtime evidence: OpenClaw disconnected runtime validation completed cleanly in the isolated runner.

Used fake placeholder env vars in the sandbox; no real credentials were exposed.

• OpenClaw is available in the runner image as OpenClaw 2026.3.24 (cff6dc9).
• The skill matched the basic OpenClaw-oriented layout checks used for disconnected validation.
• SKILL.md does not explicitly mention OpenClaw; this may still be valid, but intent is less obvious.
• No safe documented OpenClaw commands or package-script help probes were found; disconnected validation remains mostly structural.

Automated result: High Risk

Current public label: High Risk

The current label should account for both the file-level review and the fact that the sandbox runtime pass did not come back perfectly clean.

Human review: none yet

The current public label is still relying on automation. A human has not weighed in yet.

Severity mix: 2 low, 1 info