gws-tasks
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the 'gws' binary to manage Google Tasks. This is a vendor-provided tool from the skill's author (googleworkspace) and its usage is consistent with the stated purpose of the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection because it ingests user-controlled content from Google Tasks into the agent's context.
- Ingestion points: Data is brought into the agent via the
tasks list,tasks get, andtasklists listmethods documented inSKILL.md. - Boundary markers: None identified. The instructions do not define specific delimiters or warnings to treat task content as untrusted data.
- Capability inventory: The skill provides access to task management capabilities (creation, deletion, updates) via the
gwsCLI. It does not include arbitrary code execution or filesystem write capabilities. - Sanitization: No evidence of content sanitization or instruction filtering is present in the skill configuration.
Audit Metadata