14-day stale PR close
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub pull requests, including contributor comments and review text, to determine author activity timestamps.
- Ingestion points: Pull request metadata, comments, and review history are fetched from external GitHub repositories via the
ghtool (SKILL.md). - Boundary markers: The instructions lack specific delimiters or instructions to ignore potential commands embedded within the PR data being analyzed.
- Capability inventory: The skill is capable of executing
gh pr closecommands to modify repository state based on its analysis (SKILL.md). - Sanitization: No explicit requirement for sanitization or validation of external content is mentioned before processing it to calculate the activity clock.
- [COMMAND_EXECUTION]: The skill executes shell commands using the GitHub CLI tool to perform repository management tasks.
- Evidence: The skill explicitly instructs the agent to run
gh pr close <n> --repo <OWNER/NAME> --comment "<body>"using parameters derived from the invocation (SKILL.md).
Audit Metadata