every-format-delivery
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is strictly focused on video reformatting and layout management using authorized platform-specific tools such as
update_video,add_layout, andduplicate_video. No suspicious command execution, network exfiltration, or obfuscation techniques were found. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied video content, including transcripts and text overlays, which represents a potential attack surface. However, the risk is mitigated by the highly specific, procedural instructions governing the layout transformations and graphic rendering, which constrain the agent's behavior to formatting tasks.
- Ingestion points: Master's timeline data, layouts, overlays, text overlays, settings, filmstrips, and subtitles (SKILL.md).
- Boundary markers: None explicitly defined in the instructions for text processing.
- Capability inventory: Platform-specific video editing API tools; creation of video copies; network-based export and upload to the Tella service.
- Sanitization: None explicitly mentioned for transcript or overlay content.
Audit Metadata