python-code-reviewer
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured instructions for Python code review and does not contain malicious code or exfiltration patterns.- [COMMAND_EXECUTION]: Utilizes read-only tools (Read, Grep, Glob) for source code analysis, which is consistent with the skill's purpose.- [DATA_EXFILTRATION]: No evidence of hardcoded credentials or unauthorized network requests.- [PROMPT_INJECTION]: Indirect Prompt Injection Surface:- Ingestion points: The skill processes Python code files via Read and Grep tools.- Boundary markers: Absent. The instructions do not explicitly direct the agent to ignore instructions embedded within the code comments or strings.- Capability inventory: The skill utilizes Read, Grep, and Glob tools for analysis. It explicitly instructs the AI not to use Edit or Write tools unless explicitly asked.- Sanitization: None. The content of the code is processed as raw text for review.
Audit Metadata