game-mechanics-design
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process external project data, creating a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The 'Workflow' section in
SKILL.mddirects the agent to read project scenes, scripts, resources, save models, and existing tests. - Boundary markers: The instructions do not define any delimiters or 'ignore' instructions to help the agent distinguish between its core instructions and the data being analyzed.
- Capability inventory:
SKILL.md(Workflow Step 7 and Implementation Checks) identifies capabilities for file reading, file writing ('Create the smallest playable test'), and command execution ('Unit-test economy transactions'). - Sanitization: No validation or filtering mechanisms are mentioned for the content retrieved from external project files.
Audit Metadata