openstoryline-use

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local commands to manage Python services (Uvicorn and MCP server) and configuration. These are standard operations for running the local OpenStoryline application.
  • [EXTERNAL_DOWNLOADS]: The skill mentions external dependencies and model downloads but explicitly states that these are handled by a separate installation skill, and this skill only handles the usage phase.
  • [DATA_EXFILTRATION]: No data exfiltration patterns were detected. The skill instructions emphasize using 127.0.0.1 and warn against exposing services to the public network.
  • [PROMPT_INJECTION]: The instructions do not contain attempts to bypass AI safety filters or override system prompts. They provide operational guidelines for the agent's behavior during a video editing task.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 12:01 PM