uw-game-feel-integrator
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest external project data which could be manipulated to influence the agent's output.\n
- Ingestion points: The instructions in
SKILL.mdrequire the agent to readdocs/ProjectConfig.yamlanddocs/GFD.mdfor tool configuration and feedback requirements.\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between data and potential commands within these ingested files.\n
- Capability inventory: The skill involves generating C# code and potentially executing the
refresh_unitytool, which are capabilities that could be influenced by malicious input in documentation files.\n - Sanitization: The skill does not specify any sanitization or validation logic for the content of the documentation files used during prompt construction.
Audit Metadata