text-to-image

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the meitu CLI to process image generation requests, passing user-supplied text descriptions and image URLs as command arguments.
  • [SAFE]: The skill accesses configuration and credential files at ~/.meitu/credentials.json and ~/.meitu/tool-registry.json. These are vendor-specific paths required for the Meitu CLI tool to authenticate with the vendor's API and are consistent with the skill's primary purpose.
  • [SAFE]: A potential surface for indirect prompt injection exists as the skill processes untrusted user input.
  • Ingestion points: User-provided prompt and image_list parameters.
  • Boundary markers: None present; input is interpolated directly into the CLI command template.
  • Capability inventory: Execution of the meitu CLI tool (defined in SKILL.md).
  • Sanitization: No explicit sanitization or validation of the input strings is performed within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 06:03 AM
Security Audit — agent-trust-hub — text-to-image