tella-kinetic-type
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional content for video editing. No malicious patterns such as credential exfiltration, privilege escalation, or obfuscation were identified. All references to external tools and skills (tella, tella-motion-design) are consistent with the vendor's own ecosystem.
- [INDIRECT_PROMPT_INJECTION]: The skill processes video transcript data to synchronize text overlays (SKILL.md).
- Ingestion points: Video transcripts and timeline data enter the agent context via the Tella MCP
get_timelinetool. - Boundary markers: None present in the instructions.
- Capability inventory: Limited to video editing and styling actions (text overlays, motion effects) via the Tella platform.
- Sanitization: None specified for the transcript content. While this creates a theoretical surface for indirect instructions embedded in a transcript, the lack of dangerous capabilities (like shell access or network exfiltration) associated with this processing makes the pattern benign.
Audit Metadata