vp-pr-briefing
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on shell commands using
ghandgitto fetch Pull Request details, commit messages, and file differences. These commands are used to populate the briefing with context from the repository.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted data from GitHub PR bodies, comments, and commit messages.\n - Ingestion points: Pull request content is retrieved via
gh pr viewinSKILL.md.\n - Boundary markers: The instructions do not define specific delimiters for isolating external content in the briefing output.\n
- Capability inventory: The agent has access to repository tools (
gh,git).\n - Sanitization: No specific sanitization or filtering is instructed for the retrieved external data.
Audit Metadata