code-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill's primary purpose is to ingest and analyze untrusted code, which creates a surface for indirect prompt injection attacks.
- Ingestion points: Code snippets or files provided for review.
- Boundary markers: None; there are no delimiters defined to separate untrusted code from the agent's instructions.
- Capability inventory: Executes a local script 'check_style.py' via the get_skill_script function.
- Sanitization: No input sanitization or safety-filtering of the code to be reviewed is specified in the skill definition.
Audit Metadata