describe-pr-nt
Fail
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill explicitly directs the agent to identify and run shell commands (e.g.,
make check test,npm test) found within the "How to verify it" section of a pull request. Since the content of a pull request is provided by the author (who may be an untrusted external contributor), this pattern allows for the execution of arbitrary, potentially malicious code on the system where the agent is running. - [COMMAND_EXECUTION]: The skill automates the use of the GitHub CLI (
gh) to perform various repository operations, including retrieving diffs, commit history, and updating PR descriptions. The combination of automated GitHub API interactions and the execution of untrusted commands derived from PR content creates a critical security vulnerability.
Recommendations
- AI detected serious security threats
Audit Metadata