setup-for-oss
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted metadata from the repository to generate health files and CI/CD workflows. 1. Ingestion points:
package.json(name, author), git config, and pull request titles (used inlabel-pr.yml). 2. Boundary markers: Absent. 3. Capability inventory: File-write operations (SKILL.md) and GitHub APIaddLabelscall (references/ci-workflows.md). 4. Sanitization: Absent. This allows potentially malicious repository configuration to inject content into generated files or influence automated labelling. - [External Downloads] (LOW): The skill configures workflows that depend on various community-maintained GitHub Actions and npm packages. Evidence in
references/publishing.mdshows the skill correctly advises users to pin actions to specific commit SHAs to mitigate supply chain risks during releases.
Audit Metadata