coderabbit
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the GitHub CLI (
gh) to fetch repository metadata, pull request details, and review comments. These commands are essential for the skill's primary function and represent standard usage of the tool. - [EXTERNAL_DOWNLOADS]: Interacts with GitHub REST and GraphQL APIs to fetch pull request data. GitHub is recognized as a well-known and trusted service for development workflows.
- [PROMPT_INJECTION]: The skill processes external data in the form of CodeRabbit comments, creating a surface for indirect prompt injection.
- Ingestion points: Pull request review threads and walkthrough summaries fetched via GitHub APIs.
- Boundary markers: Not present; the instructions do not define delimiters to isolate untrusted comment content from the agent's instructions.
- Capability inventory: Limited to read-only GitHub API operations via
gh. The skill lacks the ability to execute shell commands from the input, modify files, or perform network operations outside of GitHub. - Sanitization: None; comment content is analyzed directly as retrieved from the API.
Audit Metadata