proxy-rotation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt demonstrates and instructs embedding credentials (username:password) directly into proxy URLs, environment variables, and code examples—meaning an agent would need to accept and emit secret values verbatim in generated commands/code, which is insecure.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs scraping public websites (e.g., Google, Amazon, LinkedIn, Instagram, news sites) and includes code like scrape_with_rotation(url, ...) that performs requests.get(url, proxies=...), so the agent would fetch and act on untrusted third‑party web content (responses/HTTP status) to decide proxy rotation and retries.