linkpix-minimax-h3-sales

Fail

Audited by Snyk on Oct 1, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the agent to ask the user for an API key/token and then execute a command using it as a direct command-line argument (qhkit config set --token <密钥> --env prod). This exposes the secret value in the command context and generated output.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (medium risk: 0.30). The skill provides a CLI tool (qhkit) to generate e-commerce promotional videos via the Qinghu AI API (e.g., MiniMax H3). Generating videos via API calls consumes credits and initiates paid tasks (qhkit video generate), which constitutes a direct financial operation (purchasing/generating paid AI assets). The skill relies on API keys set via qhkit config set --token <key> or environment variables for authentication, which establishes independent service authentication/access control.

Issues (2)

W007
HIGH

Insecure credential handling detected in skill instructions.

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
HIGH
Analyzed
Oct 1, 2026, 03:57 PM
Issues
2