wayfinder
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of processing external, user-generated content from an issue tracker.\n
- Ingestion points: In
SKILL.md, the agent is instructed to 'fetch the full body of any related or closed ticket on demand' and 'Load the map' (which is a live tracker issue).\n - Boundary markers: There are no explicit boundary markers or 'ignore' instructions defined to prevent the agent from executing instructions embedded within the fetched issue titles, descriptions, or comments.\n
- Capability inventory: The agent has broad capabilities including creating and closing issues, posting resolution comments, and triggering subagents for research and prototyping.\n
- Sanitization: The skill lacks logic to sanitize, escape, or validate the content retrieved from the issue tracker before it is integrated into the agent's context.
Audit Metadata