ghwf6-verify
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several automated shell commands including 'pnpm lint', 'pnpm build', 'pnpm test', and 'git push' to perform code verification and repository management. These commands operate on the local file system as part of the intended developer workflow.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from external sources such as GitHub Issue comments and Pull Request reviews via the 'gh' CLI. Ingestion points: 'state.json', 'gh issue view', and 'gh pr view'. Boundary markers: None. Capability inventory: shell execution ('pnpm', 'git', 'gh'). Sanitization: None. Malicious instructions embedded in these external comments could potentially influence the agent's verification results or subsequent actions.
Audit Metadata