skills/toolshell/skills/qwen-image-2/Gen Agent Trust Hub

qwen-image-2

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the AI model through the infsh CLI. The agent's capabilities are restricted to this specific tool via the allowed-tools policy, adhering to the principle of least privilege.
  • [EXTERNAL_DOWNLOADS]: Setup instructions refer to fetching the inference-sh/skills package using npx. This originates from a well-known service provider associated with the skill's purpose.
  • [PROMPT_INJECTION]: The skill ingests user text for image generation, representing an indirect injection surface. Ingestion points: prompt and negative_prompt fields in JSON inputs. Boundary markers: Data is structured in JSON format. Capability inventory: Execution of infsh in a shell. Sanitization: Handled by the backend model providers.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 01:18 PM