code-review-expert

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing untrusted data from a git repository and possessing write capabilities.
  • Ingestion points: According to the workflow in SKILL.md, the agent ingests untrusted code changes using git status -sb, git diff --stat, and git diff.
  • Boundary markers: Absent. There are no instructions to the agent to use delimiters or to disregard instructions embedded within the code or comments it analyzes.
  • Capability inventory: The skill allows the agent to execute git commands, search the codebase, and implement file changes ("Fix all" or "Fix specific items" in the Next Steps section).
  • Sanitization: Absent. No filtering or validation is performed on the code content before it is processed by the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 10:24 PM
Security Audit — agent-trust-hub — code-review-expert