wayfinder

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external issue tracker (tickets, map body, and comments) and uses this data to drive subsequent actions like research, prototyping, and implementation.
  • Ingestion points: Content is ingested from the repo's issue tracker, specifically the issue labeled wayfinder:map and its child issues (tickets).
  • Boundary markers: The skill uses markdown templates for structure (e.g., ## Destination, ## Question), but lacks explicit delimiters or instructions to ignore potential malicious prompts embedded within the issue content.
  • Capability inventory: The skill orchestrates the use of other high-capability tools including /research, /prototype, and /implement, which may involve network access or code execution.
  • Sanitization: There is no mention of sanitizing or validating the content retrieved from the issue tracker before it is passed to the agent or other skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 05:27 PM
Security Audit — agent-trust-hub — wayfinder