🔎 Evidence browser

Search the skill radar

Search by skill, publisher, category, or trust summary — then use the runtime filters to find cards with live test evidence. The two main lanes are baseline safety checks first and deeper follow-on functionality checks after that.

Security GitHub Weather Trusted only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime Hall of Shame Stronger evidence imports Needs review Clear filters

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

✨ Quick picks

Security GitHub Weather Trusted only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime Hall of Shame Stronger evidence imports Needs review Clear filters

🏷 Categories · catalog-only

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

🧾 Evidence level: source-scanned means local source evidence; catalog-only means thinner metadata-first coverage.

🧪 Runtime status: cards can show only the baseline safety lane or the deeper follow-on functionality lane, depending on how far the skill got.

📏 Depth cue: tells you whether the evidence stops at baseline checks, includes follow-on functionality checks, or includes richer fixture/example proof.

⏱ Freshness cue: tells you whether the latest runtime evidence is from the last 24 hours, the last 7 days, or is older and therefore less current.

🩺 Failure confidence: distinguishes a first seen failure from a repeated failure or a regression after an earlier pass, so not every red row means the same thing.

Results

Showing 24 of 241 results for “security” · category: catalog-only · sort: relevance

page evidence snapshotruntime-passed: 5 runtime-failed: 0 source-scanned: 24 fresh <24h: 4 manual review: 0

This snapshot is for the current page of results, not the whole filtered universe.

Browse hint: slices with zero failures plus some source-scanned or reviewed entries deserve more attention first; fresh runtime evidence helps too, because old clean receipts can still hide current drift.

anti-injection-skill

georges91560 · vsource-scanned

Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: curl |, rm -rf, password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

simple-formatter

tjade273 · vsource-scanned

Formats text according to specified style guidelines. A clean example skill with no security issues.

Trustedconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

opsecmd

wulf715 · vsource-scanned

A swift reminder of both human and agent duties regarding operational security.

Trustedconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (email), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

farnwick-skillguard

farnwickarglefax · vsource-scanned

AI-powered security scanner for OpenClaw skills. Scans skill files for credential theft, data exfiltration, reverse shells, obfuscation, and other threats before installation.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo .

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

gcp-fullstack

guifav · vsource-scanned

Full-stack super agent for projects on Google Cloud Platform with GitHub and Cloudflare — covers scaffolding, compute, database, auth, deploy, CDN, and security

High Riskfollow-on functionality checks passed · 5/5confidence: source evidence

Runtime receipts + what passed2026-03-14 14:30 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1619 msbaseline-v3 8/8

RatioDaemon on this skillGcp Fullstack is trying to handle gcp fullstack. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

friday-router

runeweaverstudios · vsource-scanned

Your AI's Smart Traffic Director—precisely matching OpenClaw tasks to the perfect LLM. Intelligent orchestration with OpenRouter. Security-focused: no gateway auth exposure.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

aiclude-vulns-scan

mastergear4824 · vsource-scanned

Search security vulnerability scan results for MCP Servers and AI Agent Skills from the AICLUDE scan database.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

hefestoai-auditor

artvepa80 · vsource-scanned

Static code analysis tool. Detects security vulnerabilities, code smells, and complexity issues across 17 languages. All analysis runs locally — no code leaves your machine.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

aegis-audit

sanguineseal · vsource-scanned

Deep behavioral security audit for AI agent skills and MCP tools. Performs deterministic

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (private key, token), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

pincer

panzacoder · vsource-scanned

Security-first wrapper for installing agent skills. Scans for malware, prompt injection, and suspicious patterns before installation. Use instead of `clawhub install` for safer skill management.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: curl |, rm -rf, password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

ipwebcam

alihmaou · vsource-scanned

Transform an Android phone with IP Webcam into an intelligent Edge AI security system with OpenClaw.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

agentaudit

starbuck100 · vsource-scanned

Automatic security gate that checks packages against a vulnerability database before installation. Use before any npm install, pip install, yarn add, or package manager operation.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence

Runtime receipts + what passed2026-03-16 03:15 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 115 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2265 msbaseline-v3 8/8

RatioDaemon muttered: agentaudit behaved itself under runtime pressure.7/7 functionality-v2 checks passed. Pleasantly boring.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: eval(, curl |, rm -rf, sudo , password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

skillfence

deeqyaqub1-cmd · vsource-scanned

Runtime security monitor for OpenClaw skills. Watches what your installed skills actually DO — network calls, file access, credential reads, process activity. Not a scanner. A watchdog.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence

Runtime receipts + what passed2026-03-16 04:45 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 97 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1946 msbaseline-v3 8/8

RatioDaemon muttered: skillfence behaved itself under runtime pressure.6/6 functionality-v2 checks passed. Pleasantly boring.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: eval(, password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

skill-hunter

kenoodl-synthesis · vsource-scanned

Find, evaluate, and install ClawHub skills. Semantic search across 10,000+ skills, security vetting before install, side-by-side comparison. The skill that makes skills useful.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: curl |.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

azhua-skill-vetter

fatfingererr · vsource-scanned

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: eval(, sudo .

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

pr-risk-analyzer

nerdvana-labs · vsource-scanned

Analyze GitHub pull requests for security risks and determine if a PR is safe to merge.

Trustedconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

ansible-skill

botond-rackhost · vsource-scanned

Infrastructure automation with Ansible. Use for server provisioning, configuration management, application deployment, and multi-host orchestration. Includes playbooks for OpenClaw VPS setup, security hardening, and common server configurations.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo , password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

minduploadedcrab-skillguard

minduploadedcrab · vsource-scanned

Security scanner for OpenClaw skills. Scans skills for malware, credential theft, data exfiltration, prompt injection, and permission overreach before installation. Run: python3 scripts/skillguard.py scan <skill-directory>

High Riskfollow-on functionality checks passed · 8/8confidence: source evidence

Runtime receipts + what passed2026-03-16 03:00 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassed, handled_fake_credentials_cleanlyoutput 143 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3116 msbaseline-v3 8/8

RatioDaemon muttered: minduploadedcrab-skillguard behaved itself under runtime pressure.8/8 functionality-v2 checks passed. Pleasantly boring.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: eval(.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

agentaudit-skill

starbuck100 · vsource-scanned

Automatic security gate that checks packages against a vulnerability database before installation. Use before any npm install, pip install, yarn add, or package manager operation.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence

Runtime receipts + what passed2026-03-16 06:00 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 115 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2336 msbaseline-v3 8/8

RatioDaemon muttered: agentaudit-skill behaved itself under runtime pressure.7/7 functionality-v2 checks passed. Pleasantly boring.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: eval(, curl |, rm -rf, sudo , password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

mayguard

balkanblbn · vsource-scanned

A security auditor for agent skills. Scans skill directories for malicious patterns (credential theft, suspicious network calls, destructive commands) and provides a safety score. Use before installing unknown skills.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: rm -rf.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

macarena-test

misirov · vsource-scanned

Security audit and threat model for OpenClaw gateway hosts. Use to verify OpenClaw configuration, exposure, skills/plugins, filesystem hygiene, and to produce an OK/VULNERABLE report with evidence and fixes.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

credence

pestafford · vsource-scanned

Check any MCP server or AI tool against the Credence trust registry before installing it. Scores security, provenance, and behavioral risk on a 0-100 scale.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

ai-boss-assistant

jacky6658 · vsource-scanned

Transform any AI into a professional executive assistant with battle-tested personas and workflows. Complete templates for Google Workspace integration (Gmail, Calendar, Drive), milestone delivery system, and security guidelines.

High Riskconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: sudo , password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

lieutenant

jd-delatorre · vsource-scanned

AI agent security and trust verification. Scan messages, agent cards, and A2A communications for prompt injection, jailbreaks, and malicious patterns. Use when protecting agents from attacks, verifying external agents, or scanning untrusted content.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

« First ← Prev 1 6 7 8 11Page 7 / 11Next →Last »