dojo-brian-chesky

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No security vulnerabilities were detected. The skill consists exclusively of instructional markdown files and contains no executable code or scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user queries to provide contextually grounded advice. Ingestion points: User input in SKILL.md is used to route to expert personas. Boundary markers: Strict instructions require the agent to use only substance from loaded files and prevent fabrication. Capability inventory: The agent is limited to reading local files (persona.md and topics/*.md). Sanitization: The agent follows a specific persona voice and framework set to maintain context integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 03:31 PM
Security Audit — agent-trust-hub — dojo-brian-chesky