dojo-annie-duke
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill package contains no executable scripts or code. All analyzed files are plain markdown text files providing instructions and educational content.- [SAFE]: No network operations, external API calls, or remote script downloads were detected. The skill does not communicate with external servers.- [SAFE]: No sensitive data exposure risks were found. The skill does not access private files, environment variables, or hardcoded credentials.- [SAFE]: Prompt injection analysis revealed no attempts to bypass safety filters, extract system prompts, or override agent behavior beyond standard persona instructions.- [SAFE]: Content analysis for obfuscation (Base64, hex, zero-width characters) was negative. All instructions and samples are provided in clear, readable text.- [SAFE]: Metadata fields in the YAML frontmatter are used appropriately for naming and description without containing malicious instructions.
Audit Metadata