voice
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of narration text, scripts, and sound effect prompts which are used to generate media assets.
- Ingestion points: Narration text in the
textparameter ofsubmit_voice, script tables and storyboards as described inreferences/video-sync.md, and sound prompts insubmit_sound. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing these inputs.
- Capability inventory: The skill uses tools to generate audio assets (
submit_voice,submit_sound) and modify the timeline (edit_item). It does not have arbitrary code execution or network exfiltration capabilities. - Sanitization: There is no mention of sanitizing, escaping, or validating the input text before synthesis.
Audit Metadata