wayfinder
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and acting upon instructions found in external data sources.
- Ingestion points: According to SKILL.md, the agent loads a 'map' (a tracker issue) and multiple 'tickets' (child issues), including their full bodies and associated resolution comments.
- Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between the agent's instructions and potentially malicious content within the issue tracker.
- Capability inventory: As detailed in SKILL.md, the agent can call the Skill tool with various modes (grilling, domain-modeling, research, prototype), modify issue states, and spawn new research subagents based on ticket content.
- Sanitization: There is no evidence of sanitization, validation, or filtering of the content retrieved from the issue tracker or local markdown files before it is processed by the agent.
Audit Metadata