skills/acedatacloud/skills/qwen-image/Gen Agent Trust Hub

qwen-image

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the mcp-qwen-image package using pip. This is a vendor-specific tool provided by the author, acedatacloud, to facilitate integration with their services.
  • [COMMAND_EXECUTION]: The documentation includes curl command examples to interact with the API at api.acedata.cloud for generating and retrieving image tasks.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: User-supplied prompts and image URLs are used as input for API requests defined in SKILL.md.
  • Boundary markers: None specified; the skill uses standard interpolation of user inputs into JSON payloads.
  • Capability inventory: The skill performs network operations by sending data to the vendor's API endpoint.
  • Sanitization: No explicit sanitization or validation logic is provided within the skill's instructions for the external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 05:41 PM
Security Audit — agent-trust-hub — qwen-image