flux-2-klein

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the @runcomfy/cli tool to interact with image generation models. Instructions specify passing user prompts as JSON payloads to prevent shell injection, and the CLI includes logic to verify output URLs against a whitelist of RunComfy domains.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts and reference image URLs, which are passed to the Flux 2 Klein model. The documentation explicitly acknowledges the risk of image-based prompt injection and provides guidance on prompting patterns to mitigate unintended behavior.
  • Ingestion points: prompt field and reference image URLs provided in the JSON input to the CLI.
  • Boundary markers: User input is encapsulated within a JSON string via the --input flag.
  • Capability inventory: Network communication with model-api.runcomfy.net and file writes to the directory specified by --output-dir.
  • Sanitization: Prompt content is treated as a JSON string; the CLI does not perform shell expansion on the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:19 PM
Security Audit — agent-trust-hub — flux-2-klein