hz-unity-project-analyzer

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted project data which creates a potential vulnerability surface.
  • Ingestion points: The agent is instructed to read various project files including README.md, CHANGELOG.md, Packages/manifest.json, and Unity asset files (SKILL.md).
  • Boundary markers: There are no instructions to wrap external content in delimiters or provide explicit 'ignore embedded instructions' warnings for the agent during the documentation process.
  • Capability inventory: The skill involves extensive file system read operations across the project and write operations to the .agent-docs/ directory.
  • Sanitization: The skill lacks instructions for validating or sanitizing the content read from external files before it is processed or written into the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 12:16 PM
Security Audit — agent-trust-hub — hz-unity-project-analyzer