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