outcome-vs-output
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed of purely instructional content and workflow guidelines. No executable code, shell commands, or network operations are present.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data in the form of user-supplied roadmap and backlog items. * Ingestion points: User-provided project lists defined in Step 1 of the workflow. * Boundary markers: None specified in the prompt instructions. * Capability inventory: None; the skill does not use any tools or scripts that could be leveraged for malicious purposes. * Sanitization: None present.
Audit Metadata