teacher-inquiry-cycle-designer

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is purely instructional and focuses on generating educational designs. It does not utilize any scripts, executables, or platform tools that could interact with the file system or network.
  • [PROMPT_INJECTION]: The skill incorporates untrusted user data via the {{inquiry_question}} and {{teacher_context}} variables. This constitutes an indirect prompt injection surface. However, the risk is mitigated by the lack of downstream capabilities. 1. Ingestion points: SKILL.md (input variables). 2. Boundary markers: Absent. 3. Capability inventory: None (text-only output). 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 10:54 PM