skills/noelrohi/skills/wayfinder/Gen Agent Trust Hub

wayfinder

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of data from an external issue tracker, which introduces a potential surface for indirect prompt injection. \n
  • Ingestion points: The instructions specify reading issue titles, bodies, and comments from the repository's issue tracker to manage the task map and individual decision tickets (SKILL.md). \n
  • Boundary markers: There are no instructions in the skill to utilize delimiters or specific guardrails to distinguish between legitimate data and potential adversarial instructions embedded within the issue content. \n
  • Capability inventory: The skill is capable of managing issue tracker states (creating, closing, and assigning tickets) and spawning sub-agents for research and prototyping, which could be misused if the agent follows instructions injected into tracker data. \n
  • Sanitization: The skill lacks explicit requirements for sanitizing, validating, or filtering external content before it is interpolated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 05:00 PM
Security Audit — agent-trust-hub — wayfinder