video-logo-add

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the meitu command-line tool to perform video processing. Evidence is found in the Execute section where it defines the meitu video-logo-add command using {video_url} and {logo_url} as arguments.
  • [COMMAND_EXECUTION]: A potential surface for command injection is identified where unvalidated user input is passed to the shell.
  • Ingestion points: The video_url and logo_url parameters are sourced from user input.
  • Boundary markers: No delimiters or safety warnings are implemented to prevent input from breaking out of the command context.
  • Capability inventory: The skill is granted exec permissions for the meitu binary.
  • Sanitization: The skill does not define any validation, escaping, or filtering for the URL parameters before they are used in the subprocess call.
  • [SAFE]: The skill reads vendor-specific configuration and credential files. Evidence includes authorized read access to ~/.meitu/credentials.json and ~/.meitu/tool-registry.json for authentication purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 06:03 AM
Security Audit — agent-trust-hub — video-logo-add