get-pr-ready
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of untrusted external content.
- Ingestion points: The skill fetches review threads, inline comments, and CI failure logs using the
ghtool as defined inSKILL.md. - Boundary markers: The instructions lack specific boundary markers or instructions to isolate potentially malicious instructions embedded in review comments from the agent's operational logic.
- Capability inventory: The skill possesses significant execution capabilities, including code modification, arbitrary test execution (command execution), committing and pushing code changes, and performing authenticated POST requests via the GitHub API (
gh api). - Sanitization: Although the skill correctly uses
jqto build JSON payloads for the API, it does not provide a mechanism to sanitize or filter the content of PR reviews which are used to guide its code changes and communication.
Audit Metadata