ai-voiceover
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected in this skill. The skill follows best practices for AI agent safety, including:
- Strong Ethics & Compliance: Explicitly forbids unconsented voice cloning and mandates AI disclosure in sensitive contexts (ads/political), reducing the risk of misuse for impersonation.
- Scope Limitation: Defines a clear boundary where the AI generates audio but does not perform automated video editing or high-privilege operations, relying on human review for final mixing.
- Defensive Design: Includes instructions to treat external input (comments, DMs, web results) as data rather than commands, which mitigates potential indirect prompt injection attacks.
- Resource Management: External references point to well-known, official services (ElevenLabs), and credentials are handled via a dedicated integration file rather than being hardcoded.
Audit Metadata