code-review
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use common CLI tools including
git,gh,make,mvn, andyarn. These tools are used for their intended purposes: obtaining code diffs, checking pull request status, running linters, and synchronizing project models within the user's local development environment. These commands are typical for a development-focused skill.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests content from external code changes and pull request metadata.\n - Ingestion points: Source code and pull request descriptions are read into the context using
git diffandgh pr viewas described inSKILL.md.\n - Boundary markers: The instructions do not define explicit delimiters or instructions to the agent to disregard commands found within the ingested data.\n
- Capability inventory: The agent can execute local shell commands and interact with the GitHub API (e.g., to post review comments).\n
- Sanitization: There is no evidence of data sanitization or validation performed on the external content before processing.
Audit Metadata