jahro-watcher

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as a documentation and code generation assistant for the Jahro Console Unity plugin. All code snippets provided are standard C# implementations for attribute declaration and object registration.
  • [PROMPT_INJECTION]: The skill includes instructions to ingest and analyze user-provided code to identify variables for monitoring. While this constitutes an indirect prompt injection surface, the risk is mitigated by the skill's specific focus on generating static C# attributes rather than executing the analyzed code.
  • Ingestion points: User-supplied C# classes and code blocks (SKILL.md).
  • Boundary markers: None defined.
  • Capability inventory: Code generation (C# attributes and registration methods); no host-level execution or network capabilities detected.
  • Sanitization: No explicit sanitization or validation of input code structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 09:26 PM
Security Audit — agent-trust-hub — jahro-watcher