review-code

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code and diffs from external sources (PRs and commits), which creates a surface for indirect prompt injection where malicious code could influence the agent's behavior.
  • Ingestion points: Code content is ingested via gh pr diff and git show in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' markers when passing code to sub-agents.
  • Capability inventory: The skill uses agents to perform file reading and pattern matching across the codebase to generate reports.
  • Sanitization: There is no explicit sanitization or validation of the ingested code content before it is processed by the analysis agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 08:41 PM
Security Audit — agent-trust-hub — review-code