wayfinder
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external issue tracker, which serves as a potential vector for malicious instructions embedded in issue titles or bodies.
- Ingestion points: The agent reads the 'map' issue body and individual 'ticket' issue bodies from the repository's tracker to orient itself and determine next steps.
- Boundary markers: The instructions do not define explicit delimiters or use 'ignore' directives to distinguish between instructions in the skill and data retrieved from the tracker issues.
- Capability inventory: The skill coordinates several subagents (/research, /prototype, /grilling, /domain-modeling) and performs tracker operations including creating, updating, and closing issues, as well as user assignment.
- Sanitization: There is no mention of sanitizing, validating, or filtering the content retrieved from the tracker before the agent processes it.
Audit Metadata