gsp-feedback-design
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided game design requirements and interaction descriptions to generate documentation. This represents an attack surface for indirect prompt injection where malicious instructions could be embedded in the design specifications processed by the agent.
- Ingestion points: The skill ingests design intent for input acknowledgment, reward signals, and state transitions.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious embedded commands in the source design data.
- Capability inventory: The skill utilizes file system capabilities to write documentation to paths such as
docs/game-studio/feedback-design.mdandchanges/<change-id>/design.md. - Sanitization: The skill does not define specific sanitization or validation logic for the content being written to the design documents.
Audit Metadata