code-review

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git commands to facilitate the code review process.
  • Evidence: Instructions include the use of git rev-parse and git diff to establish comparison points and extract code changes for analysis (SKILL.md).
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest and follow project-specific standards from external files, which represents an attack surface for indirect prompt injection.
  • Ingestion points: The agent reads AGENTS.md, CLAUDE.md, CONTEXT.md, and PR descriptions to identify review standards and specifications (SKILL.md).
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are defined.
  • Capability inventory: The skill has the capability to execute shell commands (git) based on the context found (SKILL.md).
  • Sanitization: No sanitization or filtering of the content from these documentation files is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:38 AM
Security Audit — agent-trust-hub — code-review