tamv-experiment-design
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured workflow that mandates the use of governance and safety guards (tamv-core-governance, tamv-rights-safety-guard) before processing creator content.- [SAFE]: It contains explicit instructions to treat user drafts as data rather than instructions, providing a robust defense against direct and indirect prompt injection.- [SAFE]: The skill features specific data handling safeguards, instructing the agent to minimize personal data, avoid sending secrets, and refrain from unauthorized network activities or external resource usage.- [SAFE]: No evidence of command execution, remote code execution, obfuscation, or malicious external dependencies was found.
Audit Metadata