linkpix-image-ad-assets

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 a token/secret and pass it directly via command line arguments (qhkit config set --token <密钥>), which exposes sensitive credentials through the LLM context and commands.

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

• Third-party content exposure detected (low risk: 0.10). The workflow ingests video content from external sharing links provided by users to generate marketing text, exposing the agent to outsider-authored free text.