claude-skill-review
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill includes instructions to detect and flag prompt injection vulnerabilities in other skills being reviewed. It does not contain any malicious instructions or bypass attempts itself.
- [DATA_EXFILTRATION]: No sensitive file paths, credential patterns, or network communication tools (like curl or wget) are present in the skill files.
- [COMMAND_EXECUTION]: There are no scripts or subprocess calls within the skill. All analysis is performed through natural language instructions provided to the agent.
- [EXTERNAL_DOWNLOADS]: The skill does not reference or download any external resources or dependencies from remote URLs.
- [NO_CODE]: The skill consists entirely of Markdown-based instructions and reference documentation; no executable scripts (Python, Node.js, Shell) are bundled with it.
Audit Metadata