Skills
Navigate
skills/whytryharder/superpowers/qwen-image-2/Gen Agent Trust Hub

qwen-image-2

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data (text prompts and image URIs) which are then passed to external AI models.
  • Ingestion points: Untrusted data enters the agent context through the user-supplied prompt string and the reference_images array.
  • Boundary markers: There are no explicit boundary markers or system instructions to ignore embedded commands within the ingested content.
  • Capability inventory: The skill uses the Bash tool to execute belt app run commands.
  • Sanitization: No input sanitization or validation logic is defined within the provided skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill refers to external resources for the installation of necessary CLI tools and platform extensions.
  • Evidence: Provides instructions to install belt-sh/cli via npx and links to configuration scripts hosted on the inference-sh GitHub repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 05:50 AM