Skills that still need review

This skill generates human-like images using Google AI Studio (Gemini). It creates realistic photos with natural lighting and subtle imperfections.

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 develop Apify Actors. 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: 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 documentation about Apple technologies, as part of the Apple Human Interface Guidelines.

Source: Workspace import

Originally ingested from a local workspace copy.

Automated result: Needs Review

Current public label: Needs Review

The skill's documentation references external endpoints and secrets, which warrants review to understand how they are used.

Human review: none yet

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

Severity mix: 2 medium, 19 low

This skill provides App Store Optimization (ASO) capabilities for mobile 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 analyzes audience data from multiple platforms. Driftloom found that the skill references credentials and makes outbound HTTP 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 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-focused guide, potentially including shell commands.

Source: Workspace import

Originally ingested from a local workspace copy.

Automated result: Needs Review

Current public label: Needs Review

The skill's use of potentially destructive shell commands and privilege escalation warrants human review.

Human review: none yet

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

Severity mix: 1 high, 1 medium, 1 low

This skill provides guidance on writing unit tests for shell scripts using Bats, including test patterns and best practices.

Source: Workspace import

Originally ingested from a local workspace copy.

Automated result: Needs Review

Current public label: Needs Review

The skill includes a destructive shell pattern, so it needs review to ensure it is used safely.

Human review: none yet

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

Severity mix: 1 high, 1 low

This skill scrapes reviews and brand mentions from multiple platforms using Apify Actors.

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 troubleshooting steps for Claude in Chrome MCP tools. It appears to be primarily documentation.

Source: Workspace import

Originally ingested from a local workspace copy.

Automated result: Needs Review

Current public label: Needs Review

The skill includes a destructive shell pattern, which requires human review. The documentation-heavy structure limits automated analysis.

Human review: none yet

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

Severity mix: 1 high, 1 low

This skill performs cloud penetration testing, covering reconnaissance, authentication testing, and privilege escalation techniques.

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 REST API gateway for ComfyUI servers, managing workflows, queuing jobs, and handling image delivery.

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 competitors by extracting data from multiple platforms using Apify Actors.

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 extracts engagement metrics from multiple platforms using Apify Actors.

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 guidance for building Python applications with DBOS durable workflows. It appears to be mostly documentation.

Source: Workspace import

Originally ingested from a local workspace copy.

Automated result: Needs Review

Current public label: Needs Review

The skill's use of external network resources and its documentation-heavy structure warrant a review to ensure proper operation and security.

Human review: none yet

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

Severity mix: 4 medium, 4 low

This skill provides a guide for building TypeScript applications with DBOS durable workflows. It appears to make outbound HTTP calls.

Source: Workspace import

Originally ingested from a local workspace copy.

Automated result: Needs Review

Current public label: Needs Review

The skill's use of network calls and documentation-heavy structure warrant a review.

Human review: none yet

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

Severity mix: 5 medium, 4 low

This skill helps manage dependencies by planning and executing updates. Driftloom found a destructive shell pattern in the 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 sets up a pre-configured devcontainer. It appears to be mostly documentation.

Source: Workspace import

Originally ingested from a local workspace copy.

Automated result: Needs Review

Current public label: Needs Review

The skill includes a destructive shell pattern, which requires review. The documentation-heavy structure also limits automated analysis.

Human review: none yet

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

Severity mix: 1 high, 1 low

This skill extracts product data from e-commerce platforms.

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 documentation on ethical hacking methodologies, covering reconnaissance, attack techniques, and reporting.

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 automates code quality checks using Git hooks. It aims to catch issues before commits and pushes.

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 discovers and analyzes influencers across multiple platforms. It appears to make outbound HTTP calls and references 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 scrapes leads from multiple platforms using Apify Actors. The skill's code references 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 provides production patterns for Linkerd service mesh. 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: 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 assesses Linux systems for privilege escalation vulnerabilities. It identifies weaknesses that could allow a low-privilege user to gain root access.

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