cleanup
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external version control providers which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads PR listings via
list_prsand individual PR comment histories viaget_pr_comments(SKILL.md, references/merge-verification.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when processing external PR content.
- Capability inventory: The skill has the authority to delete local git branches (
git branch -d), prune worktrees via the orchestrator, and transition internal workflow states which includes force-approving review statuses (SKILL.md). - Sanitization: There is no evidence of sanitization or strict validation of the retrieved PR data before it is used to drive the cleanup logic.
- [COMMAND_EXECUTION]: The skill executes shell commands to synchronize the local repository state with the remote provider.
- Evidence: The skill performs
git fetch --pruneandgit branch -don branches collected from the VCS metadata (SKILL.md).
Audit Metadata