gsp-feedback-design
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of design instructions for game development. It does not perform network operations, access sensitive credentials, or execute code.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided game mechanic descriptions to generate documentation. While this constitutes an ingestion surface for untrusted data, the risk is inherent to the task and mitigated by the agent's core safety guidelines.
- Ingestion points: User descriptions of game interactions and mechanics provided during conversation.
- Boundary markers: None explicitly defined within the skill instructions.
- Capability inventory: Reading local template files and writing design documentation to project-relative paths (e.g.,
docs/game-studio/andchanges/). - Sanitization: No explicit sanitization or input validation logic is present within the skill's markdown content.
Audit Metadata