cli-anything-obs-studio

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires installing the 'cli-anything-obs_studio' Python package from PyPI, which is the core component for its functionality.
  • [COMMAND_EXECUTION]: The skill utilizes several CLI commands through the 'cli-anything-obs_studio' tool to manage projects, scenes, and sources, including writing to local JSON files.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface when processing external project files. * Ingestion points: Existing project files are loaded into the agent context via the 'project open' command. * Boundary markers: There are no defined delimiters or instructions to ignore potential instructions embedded within the JSON files. * Capability inventory: The tool can perform file system writes and modify application settings. * Sanitization: No explicit validation or sanitization logic is provided for the ingested configuration data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:02 PM
Security Audit — agent-trust-hub — cli-anything-obs-studio