wayfinder

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external issue trackers, creating a surface for indirect prompt injection where malicious instructions could be embedded in ticket titles or bodies.
  • Ingestion points: The skill loads map and ticket data from the repository's issue tracker as described in SKILL.md.
  • Boundary markers: There are no explicit instructions to ignore instructions found within external ticket data or clear delimiters defined.
  • Capability inventory: The skill can modify the issue tracker and invoke other subagents or skills such as /research and /prototype.
  • Sanitization: No sanitization of the external data is performed before processing.
  • [NO_CODE]: The skill does not include any executable code or scripts, consisting only of configuration and markdown instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 04:31 AM
Security Audit — agent-trust-hub — wayfinder