sharp-edges
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): The skill consists entirely of Markdown documentation and reference patterns for identifying security vulnerabilities.
- No Executable Code: The skill does not include any Python, JavaScript, Shell scripts, or binaries. It is a pure knowledge base for the agent.
- Informational Content: All security-sensitive examples (such as hardcoded API key placeholders, sensitive file paths like
/etc/passwd, or code execution payloads likepicklestrings) are contained within Markdown code blocks as examples of what to detect in other code, rather than code to be executed by the skill itself. - Metadata: The skill is attributed to Trail of Bits, a reputable security research organization, and the metadata accurately describes the skill's contents without any poisoning or deceptive instructions.
Audit Metadata