media-craft

Fail

Audited by Snyk on Feb 16, 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's prerequisite shows an explicit CLI command (obra config set kie.apiKey YOUR_API_KEY) that requires embedding an API key directly in a command, which instructs handling secrets verbatim and matches high-risk patterns (API key passed on the command line).

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts and processes arbitrary external URLs (e.g., the Image Editing & Transformation examples use --param image_urls=, and upscaling/background removal examples accept public image URLs) and instructs the agent to parse JSON output to download and use those URLs, so the agent will fetch and interpret untrusted third-party content.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:30 AM