game-engineer
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it reads local project files (package.json and .forgewright/project-profile.json) which could contain untrusted data. Ingestion points: Grounding steps in LITE.md. Boundary markers: None identified. Capability inventory: Shell command execution (cat, jq) and code generation. Sanitization: None.
- [SAFE]: The skill performs legitimate orchestration tasks. The environment sensing is limited to standard project manifests, and the generated code follows game development best practices such as frame-independent physics and object pooling.
Audit Metadata