requesting-code-review
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes code diffs retrieved via git diff which could contain malicious instructions designed to manipulate the agent's review output or assessment.
- Ingestion points: Code changes are ingested into the subagent context via git diff output between commit hashes in code-reviewer.md.
- Boundary markers: No delimiters or instructions are used to distinguish code content from instructions or to advise the agent to ignore embedded prompts.
- Capability inventory: The agent is tasked with assessing production readiness and identifying issues, potentially allowing malicious code comments to influence the final verdict.
- Sanitization: There is no sanitization of the git diff content before it is passed to the subagent for analysis.
- [COMMAND_EXECUTION]: The skill uses local shell commands to interact with the git repository for project history and file comparisons.
- Evidence: Execution of git rev-parse and git diff as documented in SKILL.md and code-reviewer.md.
Audit Metadata