verify
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill extracts information from the body of a Pull Request (
PR_BODY) and its branch name (PR_BRANCH) to perform actions such as closing issues. This ingestion of external content constitutes an attack surface. - Ingestion points:
PR_BODYandPR_BRANCHare retrieved from GitHub via thegh pr viewcommand inSKILL.md. - Boundary markers: The skill does not use specific delimiters or instructions to ignore embedded instructions within the parsed PR content.
- Capability inventory: The skill utilizes
git worktree remove --forcefor directory cleanup,git branch -dfor branch deletion, andforge closeto modify issue statuses. - Sanitization: The skill implements a validation check using
forge show "$id"for every extracted ID before attempting theforge closeoperation, which effectively limits the impact of malicious data. - [COMMAND_EXECUTION]: The skill executes various shell commands using the
Bashtool to manage the repository state. These include switching to master, pulling updates, listing CI workflow runs, and cleaning up worktrees. These operations are aligned with the skill's primary function of post-merge verification.
Audit Metadata