code-review
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any scripts, binaries, or commands that could be executed.
- [PROMPT_INJECTION]: The skill involves processing untrusted code provided by users, which is a surface for indirect prompt injection. The risk is evaluated as safe because the skill is limited to generating text feedback and has no access to sensitive system resources or network capabilities. Ingestion point: 'target' argument in SKILL.md. Boundary markers: Absent. Capability inventory: None. Sanitization: Absent.
Audit Metadata