unity-game-production
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, command executions, or data exfiltration attempts were found. The skill operates purely as a persona/prompt guide.
- [NO_CODE]: The skill contains no scripts or executable files. All instructions are provided in markdown format.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied documentation files including docs/project-profile.yaml, docs/GDD.md, and docs/control-plane.md. While these are ingestion points for untrusted data, the skill does not use any tools or system capabilities that would allow for exploitation beyond influencing text output. Boundary markers and sanitization are absent, but the lack of capabilities (subprocess calls, file-writes, or network operations) makes this surface non-exploitable.
Audit Metadata