code-review

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core function involves reading and analyzing external, potentially untrusted code files.
  • Ingestion points: Content is ingested from external files and pull requests using the Read, Grep, and Glob tools.
  • Boundary markers: The instructions do not specify any delimiters to separate analyzed code from the agent's internal instruction set.
  • Capability inventory: The skill utilizes file system tools (Read, Grep, Glob) to access codebase content.
  • Sanitization: No mechanisms for sanitizing or escaping the content of the files being reviewed are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 01:20 PM