code-review

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted code and PR data which serves as a vector for indirect prompt injection. Maliciously crafted code comments or content could attempt to influence the agent's decision-making or bypass security logic.\n
  • Ingestion points: Pull requests, diffs, and merge requests (SKILL.md).\n
  • Boundary markers: The skill does not define clear boundaries or 'ignore' instructions for the data being reviewed.\n
  • Capability inventory: The agent is granted Bash, Read, Write, Grep, and Glob tools.\n
  • Sanitization: No sanitization or validation of the input diff content is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 01:51 PM
Security Audit — agent-trust-hub — code-review