tamv-consent-ledger

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing creator content, which acts as the untrusted ingestion point. It mitigates injection risks by instructing the agent to treat drafts as data, not instructions (boundary marker). Its capabilities are limited to permission verification and logging to a private authorized register. The workflow enforces sanitization by routing inputs through the tamv-rights-safety-guard and tamv-quality-gate skills before final processing.- [SAFE]: The skill includes explicit security guidelines, such as the prohibition of sending secrets and the requirement for explicit confirmation before executing high-impact actions like charging or voice usage.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 10:18 PM