wayfinder
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (issue trackers), creating a potential surface for indirect prompt injection.
- Ingestion points: Reads issue titles, bodies, and resolution comments from the configured issue tracker (e.g., GitHub) during both the 'Chart the map' and 'Work through the map' phases.
- Boundary markers: The skill body does not define explicit boundary markers or instructions to ignore embedded commands for the content retrieved from the external tracker.
- Capability inventory: Based on the instructions, the agent can perform network operations (API calls to issue trackers), write files (creating markdown summaries and prototypes), and invoke other skills like
/prototypeand/grilling. - Sanitization: There are no documented sanitization or validation steps for the content ingested from issue bodies or comments before it is used to influence the agent's planning and execution logic.
Audit Metadata