assets-shader-get-data

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local file system which may contain malicious instructions.
  • Ingestion points: The skill reads shader files from the project's Assets/ and Packages/ folders via the assetRef input parameter.
  • Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore embedded content when processing the returned source code.
  • Capability inventory: The tool can retrieve and return the full SourceCode of shader passes, which is then provided to the agent's context.
  • Sanitization: The skill does not mention any sanitization, filtering, or validation of the shader source code content before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends that the user install the unity-mcp-cli package from the NPM registry to function.
  • [COMMAND_EXECUTION]: The skill operates by executing shell commands via the unity-mcp-cli tool to interact with the Unity project environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 04:32 PM