scrape-codegen-analyze

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt requires the agent to read cleaned HTML and metadata and emit extracted "target_value" fields verbatim in a JSON analysis — so any secrets embedded in the page (API keys, tokens, cookies, passwords in script blocks or meta tags) would be output directly, creating an exfiltration risk.