wayfinder
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses an issue tracker as its primary source of instruction and state, creating a surface for indirect prompt injection from external content.
- Ingestion points: The skill fetches and reads issue bodies, titles, and comments during both the mapping and resolution phases ('Work through the map' section in SKILL.md).
- Boundary markers: The instructions lack explicit delimiting or safety prompts to treat issue content strictly as data, which may lead the agent to follow instructions embedded within issue tickets.
- Capability inventory: The skill has the ability to invoke specialized subagents (/research, /prototype, /grilling, /domain-modeling) and can perform write operations (creating issues, wiring dependencies) on the issue tracker.
- Sanitization: There is no evidence of filtering, validation, or sanitization of the content retrieved from the issue tracker before it is processed by the agent.
Audit Metadata