anti-bot-evasion

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt contains explicit proxy credential fields (username/password placeholders) and instructs configuring proxies/browser sessions, which would require substituting and outputting real secret credentials verbatim in generated configs/commands.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content is explicitly malicious: it provides step-by-step operational guidance, proxy providers, and technical techniques (TLS/HTTP/browser fingerprint spoofing, behavioral mimicry, sticky sessions) designed to bypass anti-bot protections and enable unauthorized scraping/data exfiltration.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to use a browser tool to navigate and interact with arbitrary target websites (e.g., "Navigate to the page", "let JavaScript fully execute before extracting", and the curl example against https://target-site.com), so it fetches and interprets untrusted public web content that can alter subsequent actions.