wayfinder
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill coordinates complex workflows by invoking other specialized skills, including
/research,/prototype, and/grilling, to process specific ticket types.\n- [PROMPT_INJECTION]: The skill processes data from an external issue tracker, which constitutes an indirect prompt injection surface.\n - Ingestion points: Reads issue bodies, comments, and labels from the tracker as described in SKILL.md.\n
- Boundary markers: Uses structured markdown headers to separate the map destination, notes, and decisions.\n
- Capability inventory: The skill can create, update, and close issues on the tracker, and invokes sub-agents for external research and prototyping.\n
- Sanitization: No explicit content sanitization or escaping instructions are provided for data retrieved from the tracker.
Audit Metadata