recipe-review-overdue-tasks
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code or automated scripts; it serves as a procedural guide for task management. There are no signs of credential harvesting, unauthorized network access, or persistence mechanisms.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests task content from an external provider. Ingestion points: Tasks are listed via gws in SKILL.md. Boundary markers: None specified in the instructions. Capability inventory: Limited to listing tasks and lists. Sanitization: Not explicitly defined in the manual steps.
Audit Metadata