skills/pmprompt/claude-plugin-product-management/feature-prioritization-assistant/Gen Agent Trust Hub
feature-prioritization-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of natural language instructions for the RICE (Reach, Impact, Confidence, Effort) prioritization framework. It does not utilize any tools, scripts, or network capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data by requesting user-supplied feature lists for evaluation.
- Ingestion points: User input is ingested via the 'Features to evaluate' section in SKILL.md.
- Boundary markers: Present. The skill uses clear markdown headers and numbered list instructions to separate its logical framework from the user-provided data.
- Capability inventory: None. The skill does not define any allowed tools, subprocess calls, or network operations.
- Sanitization: None detected; however, the lack of operational capabilities (file access, network, or code execution) renders the injection surface non-exploitable.
Audit Metadata