wayfinder

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a purely instructional workflow for task decomposition and project management. No evidence of obfuscation, hardcoded credentials, or malicious commands was found.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes data from external or user-controlled issue trackers.
  • Ingestion points: Issue tracker titles, ticket descriptions, and resolution comments as described in the '推进地图' (Advance Map) section.
  • Boundary markers: Uses structured Markdown headers (e.g., ## Destination, ## Decisions so far) to organize ingested data, though it does not explicitly instruct the agent to ignore instructions embedded within those data fields.
  • Capability inventory: The skill can create and close issues on the tracker and invoke specialized sub-agents such as /research and /prototype.
  • Sanitization: The instructions do not specify any validation or sanitization steps for the data retrieved from the issue tracker.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 02:16 AM
Security Audit — agent-trust-hub — wayfinder