code-review-expert

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local git and ripgrep (rg) commands (e.g., git diff, git log, rg) to inspect the repository and build context for reviews. These operations are well-scoped to the stated purpose of the tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes untrusted data from git diffs and codebase files. (1) Ingestion points: Context is built via git commands and code search in SKILL.md and review-flow.md. (2) Boundary markers: Absent; there are no specific delimiters to separate untrusted code from instructions. (3) Capability inventory: The agent can execute git/rg shell commands and read files. (4) Sanitization: Absent. This risk is inherent to the use case and is mitigated by the structured 'findings-first' output requirement.
  • [SAFE]: No evidence of hardcoded credentials, remote code execution from untrusted sources, or obfuscation was detected across the skill's files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 09:33 AM
Security Audit — agent-trust-hub — code-review-expert