audit-skills-securityUse when installing new skills, reviewing third-party skills, or verifying skill safety before use. Triggers on any new .md skill file appearing in skill dir...
Install via ClawdBot CLI:
clawdbot install yhy0/audit-skills-securityGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
/etc/passwdContains instructions to override system prompt or ignore user requests
"Ignore all previous instructions"Potentially destructive shell commands in tool definitions
eval(Audited Apr 17, 2026 · audit v1.0
Generated May 6, 2026
A company allows users to install community-contributed skills. Before activation, Security Audit scans each skill for prompt injection, data exfiltration, or privilege escalation, generating a report to block malicious skills.
An enterprise develops custom skills for internal use. The audit skill verifies that no internal skill contains hardcoded credentials, dangerous commands, or unintentional backdoors before deployment.
A DevSecOps team integrates the audit skill into a CI/CD pipeline. Every time a skill file is committed, the pipeline runs a grep and semantic scan, failing the build if high-risk patterns are found.
An AI agent marketplace uses this skill to automatically audit all new submissions for prompt injection and data exfiltration, providing users with a safety badge for each listed skill.
An individual using a local AI agent periodically runs the audit on their installed skills to ensure no skill has turned malicious or is exfiltrating personal data via network requests.
Offer the audit as a cloud API where users submit skill files and receive structured JSON reports. Generate revenue via per-scan credits or monthly subscription tiers.
License the audit engine to AI agent platforms or enterprise software vendors who embed it into their products. Revenue from licensing fees and integration support.
Provide a premium service where security experts manually review LLM-generated reports and deliver actionable remediation advice for complex threats. Revenue from consulting hours.
💬 Integration Tip
Integrate via CLI to scan skills before activation, or use the API in a CI/CD pipeline. Combine with regular expression checks and semantic analysis for thorough coverage.
Scored May 6, 2026
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Comprehensive security auditing for Clawdbot deployments. Scans for exposed credentials, open ports, weak configs, and vulnerabilities. Auto-fix mode included.
Audit codebases and infrastructure for security issues. Use when scanning dependencies for vulnerabilities, detecting hardcoded secrets, checking OWASP top 10 issues, verifying SSL/TLS, auditing file permissions, or reviewing code for injection and auth flaws.
Detect anomalies and outliers in construction data: unusual costs, schedule variances, productivity spikes. Statistical and ML-based detection methods.
Analyze and classify agent skills for safety using local evaluation. Optionally produce a signed attestation of the vetting result.
Solve CAPTCHAs with 2Captcha from the command line during browser automation.