linkpix-seedance-25-clone

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to ask the user for an API key and then pass it directly as a command-line argument to a CLI tool (qhkit config set --token <密钥>), which exposes the secret value in the command context.

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

• Third-party content exposure detected (low risk: 0.10). The workflow ingests a user-supplied social media sharing link (resourceUrl in video-inspire generate) and passes it to the CLI tool to fetch and analyze external video content.