security-review

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a standard workflow for security audits, including OWASP Top 10 scans and secrets detection.
  • [NO_CODE]: The skill ships no executable scripts or binaries.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface. 1. Ingestion points: The agent processes external codebases provided as input. 2. Boundary markers: The prompt lacks delimiters to isolate audited code from instructions. 3. Capability inventory: The agent can delegate tasks and call MCP tools like ask_codex. 4. Sanitization: No sanitization of input code is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 04:40 PM