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