recipe-review-overdue-tasks
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Google Tasks, which creates a surface for potential indirect prompt injection if task titles or descriptions contain malicious instructions.
- Ingestion points: Data is retrieved via the
gws tasks tasks listcommand (SKILL.md). - Boundary markers: No specific delimiters or instructions to ignore external content are defined in the recipe steps.
- Capability inventory: The skill is configured to list and read task information using the
gwsutility. - Sanitization: The skill does not explicitly sanitize or filter the content retrieved from the Google Tasks API before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill uses the
gws(Google Workspace) command-line interface to interact with the Google Tasks API. These commands are necessary for the skill's primary function of retrieving productivity data.
Audit Metadata