tamv-lesson-design

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external educational material which represents a potential injection surface. However, it incorporates explicit security controls by instructing the agent to treat drafts as data rather than instructions and to apply a safety guard (tamv-rights-safety-guard) before processing content.
  • [SAFE]: The skill focuses on workflow management and educational design with a strong emphasis on data minimization and privacy. It does not contain any code execution, network exfiltration patterns, or obfuscation techniques.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 10:18 PM