roadmap-planner
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected. The skill is purely instructional and logic-based for product management tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface but no dangerous capabilities to exploit.
- Ingestion points: Accepts PRDs, stakeholder briefs, competitive reports, and backlog items (SKILL.md).
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: No subprocess calls, file system access, or network operations are requested or used.
- Sanitization: No specific input sanitization is described.
Audit Metadata