code-review

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data such as git diffs, commit messages, and documentation files, which constitutes an attack surface for indirect prompt injection. However, the risk is inherent to the tool's function and it does not possess high-privilege capabilities that could be abused through this vector.
  • Ingestion points: Git diff output, commit logs, and documentation files located in docs/, specs/, and .scratch/.
  • Boundary markers: The instructions for the analysis sub-agents do not include explicit delimiters or instructions to ignore potential commands embedded within the code or specifications being reviewed.
  • Capability inventory: The agent uses standard version control tools (git) and invokes secondary agents for specialized text analysis.
  • Sanitization: Ingested repository data is not sanitized before being passed to sub-agents, relying on the agents' own parsing capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 06:21 AM
Security Audit — agent-trust-hub — code-review