gws-tasks
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Google Tasks which could contain untrusted instructions.
- Ingestion points: Task titles, descriptions, and list names retrieved via
gws tasks list,gws tasklists list, andgws tasks getcommands inSKILL.md. - Capability inventory: The skill has the capability to delete, create, and update tasks and task lists using
gws tasks <method>andgws tasklists <method>. - Boundary markers: There are no instructions in the skill defining delimiters or markers to separate retrieved task data from agent instructions.
- Sanitization: No sanitization or filtering logic is specified for the data returned by the Google Tasks API.
Audit Metadata