recipe-review-overdue-tasks
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a workflow template (recipe) for managing Google Tasks using standard 'gws' CLI commands. No suspicious commands, network exfiltration, or unauthorized file access patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (Google Task titles and descriptions) which represents a potential attack surface for indirect prompt injection. However, the instructions focus on listing and manually reviewing data, with no automated write actions or high-privilege operations triggered by the content of the tasks.
Audit Metadata