game-project-audit
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted game project files, creating an indirect prompt injection surface.\n
- Ingestion points: Reads all files within an existing game project (source code, assets, docs) for multi-dimensional auditing.\n
- Boundary markers: No delimiters or isolation instructions are present to distinguish project data from the agent's operational instructions.\n
- Capability inventory: The skill utilizes shell/build access and file-write access, particularly in 'audit-and-patch' mode.\n
- Sanitization: No sanitization or validation of project content is performed before processing.\n- [COMMAND_EXECUTION]: The skill explicitly includes shell and build access capabilities to improve evidence quality during audits and to perform patches on project files.
Audit Metadata