skills/ethan-rio/skills/wayfinder/Gen Agent Trust Hub

wayfinder

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from an external issue tracker, which serves as an untrusted ingestion point for potential malicious instructions.
  • Ingestion points: The agent retrieves and processes the body of the 'wayfinder:map' issue and individual 'decision tickets' from the issue tracker.
  • Boundary markers: The instructions lack explicit delimiters or warnings to the model to ignore potential instructions embedded within the ticket data retrieved from the tracker.
  • Capability inventory: The skill has broad capabilities including creating issues, posting comments, closing issues, and invoking subagents (/research, /prototype, /grilling) that can perform file system operations (git branch creation) and broader research tasks.
  • Sanitization: There is no specified validation or sanitization of content retrieved from the issue tracker before it is processed by the agent or used to influence subsequent decision-making steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 10:55 AM
Security Audit — agent-trust-hub — wayfinder