videodb-skills

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the videodb Python package and python-dotenv from standard registries. It also uses npx to add the video-db/skills component, which is standard for the installation of this specific toolset.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests untrusted data from external sources like YouTube and remote video URLs via the Upload capability in SKILL.md. There are no explicit boundary markers or sanitization steps described in the instructions. The skill utilizes transcription and AI media generation capabilities, which could potentially process and act upon malicious instructions embedded within the audio or metadata of the ingested files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 08:50 AM
Security Audit — agent-trust-hub — videodb-skills