wayfinder
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and acts upon content retrieved from an external issue tracker, such as ticket titles and bodies. This creates a risk where malicious instructions embedded in the tracker content could influence the agent's behavior. * Ingestion points: Issue tracker content (SKILL.md sections on Map and Tickets). * Boundary markers: Absent; the agent is not instructed to treat ticket content as strictly data. * Capability inventory: Ability to create issues, push git branches, and spawn sub-agents. * Sanitization: No content filtering or validation is described.
- [DYNAMIC_EXECUTION]: The skill programmatically spawns research sub-agents based on the contents of specific tickets. This dynamic delegation of tasks allows the agent's behavior to be shaped by external input at runtime.
Audit Metadata