open-pr
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, specifically git commit messages via
git logand pull request comments via the GitHub API. This constitutes an indirect prompt injection surface where a third-party contributor could embed malicious instructions in a commit or comment to influence the agent's PR generation or review behavior. - [COMMAND_EXECUTION]: The skill relies on shell command execution using standard tools (
gitandgh) to interact with the local repository and the GitHub platform. While this is the primary purpose of the skill, it allows the agent to perform actions such as pushing code and posting API requests based on its analysis of the workspace.
Audit Metadata