wayfinder

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external environments.
  • Ingestion points: The skill reads from third-party APIs, external documentation, and local knowledge bases during the 'Research' task, and processes human input and issue comments during 'Grilling' sessions (File: SKILL.md).
  • Boundary markers: There are no instructions for the agent to utilize delimiters or safety headers when interpreting content retrieved from external or collaborative sources.
  • Capability inventory: The skill can spawn sub-agents for research, create and modify issues on a tracker, and invoke external tools for domain modeling and prototyping (File: SKILL.md).
  • Sanitization: The instructions do not define any validation or filtering logic for data retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 09:30 AM
Security Audit — agent-trust-hub — wayfinder