task-digest-guide
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats identified. The skill acts as a reference for a platform extension.
- [INDIRECT_PROMPT_INJECTION]: The skill aggregates data from a task list (task_list) which contains untrusted external input.
- Ingestion points: Data enters through the
task-digest-collectscript (SKILL.md). - Boundary markers: No specific boundary markers or 'ignore' instructions are provided in the guide.
- Capability inventory: No file writes, subprocess execution, or network operations are present in the skill content.
- Sanitization: The skill does not implement specific sanitization, but its function is limited to count and summary aggregation.
Audit Metadata