tella-launch-video
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a secure human-in-the-loop pattern, requiring the agent to present a plan and wait for explicit user approval ('wait for a go') before performing any write operations or video modifications.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted user content, including website URLs and product information, to drive video planning and content creation. However, the instructions mitigate this by requiring the use of placeholders for unverified details and focusing the processing on visual/brand extraction rather than executable logic.
- [SAFE]: All referenced tools and sub-skills (e.g., tella-auto-cut, tella-plan-video) are part of the intended Tella MCP ecosystem, and no unauthorized external command execution or remote script downloads are present.
Audit Metadata