skill-bundle-packager
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (LOW): The skill identifies an indirect prompt injection surface (Category 8). Ingestion points: Mission names and skill lists provided as command-line arguments in SKILL.md. Boundary markers: None present in the instructions. Capability inventory: File bundling, execution context creation, and deployment. Sanitization: Verifiable sanitization is absent as the core logic in bundle.cjs was not included in the provided files.
Audit Metadata