game-design
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill's primary function is to guide the user through a series of questions to produce a Game Design Document.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user input to generate documentation, which represents a potential surface for indirect prompt injection if the generated document is used as input for subsequent agent actions.
- Ingestion points: User input captured via the
/grill-meinteractive interview workflow defined inSKILL.md. - Boundary markers: None explicitly defined for the generated
GDD.mdcontent. - Capability inventory: File-write capability identified (saving
GDD.mdin the workspace root as specified inSKILL.md); no other sensitive capabilities or system-altering tools are invoked. - Sanitization: No specific sanitization or filtering of user input is mentioned before interpolation into the
GDD.mdtemplate.
Audit Metadata