crawl4ai

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples that embed secrets verbatim (e.g., api_token: "your-token", login js_code with username/password, proxy_config username/password), which requires placing API keys/passwords directly into configs/commands and therefore forces the LLM to handle or output secret values.

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

• Third-party content exposure detected (high risk: 0.95). At runtime, the skill crawls user-supplied URLs and ingests the fetched page content (e.g., converted to markdown/html) into the agent’s LLM context, which is outsider-authored free text from public web pages.