unity-camera

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
  • Ingestion points: String parameters such as 'objectName', 'name', 'path', and 'savePath' (found in SKILL.md) allow untrusted data from the scene hierarchy or user input to enter the agent context.
  • Boundary markers: No explicit delimiters or instructions are provided to distinguish between data and potential embedded instructions.
  • Capability inventory: The skill includes a file-writing capability through the 'camera_screenshot' tool and various Unity scene manipulation tools.
  • Sanitization: There is no evidence of path validation or input sanitization for parameters that control filesystem or hierarchy operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 11:28 PM