wayfinder
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and acts upon content from external ticket trackers (such as GitHub Issues) which can be modified by third parties.
- Ingestion points: The agent reads ticket bodies, comments, and tracker metadata to update the 'shared map' and resolve decisions.
- Boundary markers: There are no explicit instructions for using boundary markers or delimiters to separate the agent's instructions from the untrusted ticket content.
- Capability inventory: The agent has the capability to modify tracker content, invoke subagents like /research, and perform manual tasks described in the tickets.
- Sanitization: The skill body does not define any sanitization or validation logic for the data retrieved from the external ticket tracker.
Audit Metadata