wayfinder
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where malicious instructions could be embedded in the issue tracker data it processes.\n
- Ingestion points: The agent reads issue titles, bodies, and comments from a repository's issue tracker (referenced in SKILL.md).\n
- Boundary markers: The instructions lack explicit boundary markers or delimiters to differentiate between legitimate project data and potential instructions embedded in issue content.\n
- Capability inventory: The skill possesses the ability to create and modify issues, manage assignments, and spawn research subagents.\n
- Sanitization: There is no evidence of sanitization or filtering for the data retrieved from external issues before it is used to influence the agent's decision-making process.
Audit Metadata