dojo-annie-duke
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists exclusively of text-based Markdown documents for personas and frameworks. It lacks any scripts, executable binaries, or configuration-driven automation.
- [DATA_EXFILTRATION]: No network operations, API interactions, or access to sensitive local information (e.g., credentials or .env files) were found.
- [PROMPT_INJECTION]: The instructions are standard for persona-based advice. No patterns of jailbreaking, system prompt extraction, or safety filter overrides were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input for decision coaching. 1. Ingestion points: User queries in SKILL.md. 2. Boundary markers: Not present. 3. Capability inventory: No dangerous tools, network access, or write actions are enabled. 4. Sanitization: Not present.
Audit Metadata