gws-tasks
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes task data which could contain instructions from external sources, creating a surface for indirect prompt injection.
- Ingestion points: Task and task list content retrieved through the
gws tasks tasklists list/getandgws tasks tasks list/getcommands. - Boundary markers: The skill documentation does not define specific delimiters or warnings to distinguish user data from agent instructions.
- Capability inventory: The skill allows for management of tasks (creating, updating, and deleting) using the
gwsCLI but does not provide access to administrative shell commands, sensitive local files, or external network operations. - Sanitization: No validation or escaping of the task data is mentioned before the agent processes it.
Audit Metadata