phaser4-game-audio
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data including resource registration packages and authorization records.
- Ingestion points: The skill reads project-level data including 'Work Item', '项目规格' (Project Specs), and '资源登记' (Resource Registry) mentioned in SKILL.md.
- Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between instructions and the data being processed.
- Capability inventory: The skill includes capabilities to read project files and generate metadata packages that are written to shared registries.
- Sanitization: There is no evidence of sanitization or validation for the content contained within the audio resource metadata or source records.
Audit Metadata