videodb

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute Python code via the Bash tool to manage media assets and perform server-side processing using the VideoDB SDK.
  • [EXTERNAL_DOWNLOADS]: The documentation specifies installing the videodb and python-dotenv packages from the public Python Package Index (PyPI).
  • [PROMPT_INJECTION]: The skill handles untrusted external media (e.g., via coll.upload and connect_rtstream in SKILL.md), creating a surface for indirect prompt injection. The agent is granted shell execution capabilities (Bash) to process this data, though no explicit sanitization logic is provided in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 07:08 PM