pr
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, specifically linked issues and existing codebase context, to generate pull request descriptions. This data could contain malicious instructions designed to influence the agent's behavior during the PR creation process.
- Ingestion points: Linked GitHub issues, repository code, and PR templates.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested text.
- Capability inventory: The skill utilizes
gitandgh(GitHub CLI) to perform file changes, commits, and PR publishing. - Sanitization: No sanitization or validation of the ingested issue content is mentioned.
- [COMMAND_EXECUTION]: The skill requires the execution of repository-specific scripts (e.g.,
scripts/verify-*.tsx) and command-line tools likeghandgitto perform its primary functions, including verification and PR management.
Audit Metadata