kanby
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Kanby task management service, which could be used to influence agent behavior through embedded instructions.
- Ingestion points: Several commands retrieve external content into the agent's context, including
kanby task list,kanby task get(titles and notes),kanby task checklist(criterion text), andkanby activity(historical event logs and GitHub evidence). - Boundary markers: The instructions do not include specific delimiters or "ignore embedded instructions" warnings when processing the data returned by the Kanby CLI.
- Capability inventory: The agent possesses tool capabilities to mutate the task board, including creating, updating, and completing tasks, as well as linking external URLs to tasks.
- Sanitization: No sanitization, escaping, or validation of the fetched task content is required or described before the agent acts upon the information.
Audit Metadata