dojo-david-goggins
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No significant security issues were detected. The skill follows standard patterns for persona-based advice and local document retrieval.\n- [PROMPT_INJECTION]: The skill includes a 'Review' mode designed to evaluate user-provided documents, which is a potential surface for indirect prompt injection. This is a common pattern for document analysis skills but represents a potential attack surface if the agent is given broader tool capabilities.\n
- Ingestion points: User-supplied text and documents provided for critique in the 'Review' mode (SKILL.md).\n
- Boundary markers: The instructions lack defined delimiters or warnings to ignore instructions embedded within the reviewed user content.\n
- Capability inventory: The agent performs local file reads of persona and topic files and generates text outputs; it does not invoke dangerous tools or system commands across any of its 14 files.\n
- Sanitization: No validation or sanitization of the input text is implemented.
Audit Metadata