wayfinder
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill architecture relies on ingesting content from an external issue tracker, which serves as an attack surface for indirect prompt injection.
- Ingestion points: The skill fetches the map issue body and the full bodies of related or closed tickets from the repository's issue tracker during the 'Work through the map' process (defined in SKILL.md).
- Boundary markers: There are no instructions or patterns provided to the agent to distinguish between its own system instructions and potentially adversarial instructions embedded in the ticket descriptions or comments.
- Capability inventory: The agent has the ability to create and modify issues, manage task dependencies, post comments, and invoke internal subagents using the Skill tool (e.g., 'research', 'prototype').
- Sanitization: The instructions lack requirements for sanitizing or escaping the data retrieved from the tracker before it is interpolated into the agent's context.
Audit Metadata