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 viaqhkit config set --token <key>or environment variables for authentication, which establishes independent service authentication/access control.
Issues (2)
W007
HIGHInsecure credential handling detected in skill instructions.
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata