understanding-by-design

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions focus on educational design patterns, such as identifying enduring understandings and creating performance tasks. No malicious behaviors or security vulnerabilities were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined course topics to generate lesson plans. This represents a standard input surface for an AI agent, and the skill includes specific structural constraints (UbD stages) that guide the generation process without exposing sensitive data or system functions. Ingestion points: User-provided course topics and lesson requirements. Boundary markers: None explicitly defined for untrusted input. Capability inventory: Generates content via slide, quiz, interactive, and pbl tools. Sanitization: None mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 10:40 AM
Security Audit — agent-trust-hub — understanding-by-design