wayfinder
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its 'Research' ticket type, which involves ingesting untrusted data from external sources.
- Ingestion points: Instructions direct the agent to read third-party APIs and documentation (File: SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from obeying commands that might be embedded in the research data.
- Capability inventory: The skill possesses the ability to create and modify files in the docs/specs/ directory and call other specialized agent skills (File: SKILL.md).
- Sanitization: There are no requirements for sanitizing or escaping the data retrieved from external sources before it is appended to the map or tickets.
- Remediation: Use clear delimiters when incorporating research findings and explicitly instruct the agent to treat such content as data rather than instructions.
Audit Metadata