problem-framing-canvas
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructions and templates for facilitating a workshop. No executable scripts, network operations, or sensitive file access patterns were detected. It references an external source repository on GitHub for attribution purposes.
- Source: https://github.com/deanpeters/product-manager-skills
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data as it asks the user to provide problem context and stakeholder research. While it lacks sanitization, the risk is negligible as the skill does not have access to sensitive capabilities like file writing, network requests, or command execution.
- Ingestion points:
SKILL.md(Step 0: Gather Context). - Boundary markers: Absent.
- Capability inventory: No file-write, network, or subprocess capabilities detected in the skill logic.
- Sanitization: Absent.
Audit Metadata