wayfinder
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and act upon data from an external issue tracker. 1. Ingestion points: Ticket titles, descriptions, and comments parsed by the agent. 2. Boundary markers: No delimiters are specified to isolate tracker content from instructions. 3. Capability inventory: The agent can create/close issues, spawn research subagents, and call other tools. 4. Sanitization: No sanitization of the input data is mentioned.
- [DYNAMIC_EXECUTION]: The skill uses content from the map's Notes section to determine which other skills to invoke via the Skill tool. This allows the agent's functionality to be dynamically expanded based on external strings, representing a controlled form of dynamic tool selection.
Audit Metadata