python3-review
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted input in the form of code files provided via the $ARGUMENTS parameter.\n
- Ingestion points: External files specified by the user are ingested into the model context via SKILL.md.\n
- Boundary markers: Untrusted input is structurally delimited using
<review_targets>tags.\n - Capability inventory: The skill facilitates the reading and comprehensive analysis of external file content.\n
- Sanitization: There are no explicit instructions or sanitization logic to prevent the model from following potentially malicious directives embedded within the code files being reviewed.
Audit Metadata