coderabbit
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the CodeRabbit installation script directly from the service's official domain (
https://cli.coderabbit.ai/install.sh). This is the standard installation method for the tool and targets a well-known service domain. - [COMMAND_EXECUTION]: The bundled Python script (
scripts/run_coderabbit.py) executes thecoderabbitCLI using thesubprocessmodule. The script uses a list of arguments rather than a shell string, which is a security best practice to prevent command injection. It also enforces a timeout and restricts output file creation to a specific directory (.code-review/) using filename sanitization. - [INDIRECT_PROMPT_INJECTION]: The workflow involves the agent reading AI-generated output from the CodeRabbit CLI and using those findings to modify the codebase. This creates an ingestion surface where malicious content embedded in the code under review could theoretically influence the agent's behavior. However, the skill includes structured triage instructions (
references/triage.md) and recommends manual verification of all fixes, which serves as a mitigation for this risk.
Audit Metadata