flux-2-klein

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill requires the global installation of the @runcomfy/cli Node.js package. While the package version is not specified, it is an official tool from the vendor '@runcomfy' used for Model API interaction.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes user-provided text and image URLs.
  • Ingestion points: The skill accepts user prompts and reference image URLs as inputs for the image generation process.
  • Boundary markers: There are no explicit instructions provided to the agent to treat external data as untrusted instructions.
  • Capability inventory: The skill leverages the @runcomfy/cli tool to interact with the RunComfy API and save generated assets to the local disk.
  • Sanitization: Input is treated as a JSON string to mitigate shell injection risks during CLI execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:57 AM
Security Audit — agent-trust-hub — flux-2-klein