wayfinder
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests data from local markdown files (tickets and maps) stored in the project's 'plans/' directory. These files serve as ingestion points for the agent's context during the 'Work Through the Map' phase. While the skill uses markdown headers like 'Question' and 'Resolution' to structure this data, there is a theoretical surface where malicious instructions embedded in these files by an external actor could influence the agent's behavior. However, this surface is a inherent part of the skill's planning function and is mitigated by strict operational rules that prioritize user control.
- [DYNAMIC_EXECUTION]: The skill orchestration involves the invocation of other registered skills and the spawning of sub-agents for automated research (e.g., using the
$web-researchtool). These are standard platform-provided capabilities for skill composition and task delegation, used here to support the breadth-first mapping and investigation process.
Audit Metadata