unity-implement-batch

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from task files located in the docs/<feature-slug>/tasks/ directory, which are used to guide subagents in performing actions such as code editing and command execution.
  • Ingestion points: Markdown files in the docs/<feature-slug>/tasks/ directory (SKILL.md).
  • Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the content of these files from the agent's internal logic.
  • Capability inventory: The subagents have the ability to edit .cs scripts and tests directly, and use the /unity-cli tool to modify various Unity project files (SKILL.md).
  • Sanitization: There is no instruction to sanitize, validate, or escape the content of the task files before the agent processes them.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 02:34 AM
Security Audit — agent-trust-hub — unity-implement-batch