skills/tellahq/skills/tella-short/Gen Agent Trust Hub

tella-short

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill defines a standard editing workflow for the Tella video platform. It requires user confirmation for the editing plan and credit-usage, which limits autonomous risk.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from transcripts and external URLs. Ingestion points: Video transcripts (get_transcript) and website content (import_from_url). Boundary markers: User approval of the scene-by-scene plan before execution. Capability inventory: Video modification tools including duplication, trimming, and layout updates. Sanitization: Verification is performed manually by the agent against a checklist during the Check phase.
  • [EXTERNAL_DOWNLOADS]: Uses import_from_url to fetch B-roll content from product websites. This is described as a functional requirement for sourcing assets from official pages.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 02:51 AM