audit-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository being reviewed, serving as an ingestion point for data that could contain malicious instructions designed to influence the agent's review verdict.
- Ingestion points: Git diffs, commit logs, and local documentation files like README.md and CONTRIBUTING.md are read into the agent context.
- Boundary markers: The instructions do not explicitly mandate the use of delimiters or specific warnings to ignore instructions embedded within the code hunks being reviewed.
- Capability inventory: The agent has access to repository tools such as git, grep, and SemanticSearch, as well as external integrations for issue searching via Sentry and web research via Firecrawl.
- Sanitization: No automated sanitization or filtering is performed on the ingested code or documentation content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute standard version control commands to gather necessary context for the audit.
- Evidence: Use of git log and git diff to analyze recent changes and file statistics.
- [EXTERNAL_DOWNLOADS]: The skill integrates with external platforms to enhance the review process with production data and research.
- Evidence: Retrieves issue data from Sentry's API and performs web searches via Firecrawl to research current best practices.
Audit Metadata