zr-create-tasks
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and commands are consistent with its stated purpose of project task management.
- [SAFE]: No sensitive data exposure, exfiltration, or unauthorized command execution patterns were found.
- [SAFE]: The skill does not perform external network requests or download third-party code.
- [PROMPT_INJECTION]: The skill processes project objectives which constitutes an attack surface for indirect prompt injection, though it is a standard functional requirement for this task. 1. Ingestion points: Project objective and constraints from probe project get (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Task creation and messaging via probe CLI (SKILL.md). 4. Sanitization: Absent.
Audit Metadata