Nutritionist

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized commands were detected across the analyzed files.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided health and dietary information (defined in SKILL.md).
  • Ingestion points: User input regarding eating patterns, goals, and history.
  • Boundary markers: None explicitly defined.
  • Capability inventory: None. The skill does not use any tools, file system operations, or network requests.
  • Sanitization: None specified, but the lack of executable capabilities renders this surface non-exploitable for system-level attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 05:22 AM
Security Audit — agent-trust-hub — Nutritionist