setup

Fail

Audited by Snyk on Feb 27, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt explicitly asks the user to paste API tokens/keys (e.g., meigen_sk_, sk-...) and then instructs the agent to embed those values verbatim into a saved JSON config and use a Write tool (and to parse curl commands to extract keys), which requires the LLM to handle and output secrets directly.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill's required Step 3B-2 ("Import Workflow") asks the agent to import and parse user-supplied ComfyUI workflow JSON files (potentially downloaded from public/shared sources) and then uses the detected nodes and parameters to control image-generation tools, so untrusted third-party content can directly influence tool behavior.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 27, 2026, 01:40 PM