captcha-solving

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill explicitly automates CAPTCHA circumvention by extracting challenge assets and page state, sending them to third‑party solver services (2Captcha/SadCaptcha), and injecting returned tokens/clicks into target pages — behavior intended to bypass anti‑abuse controls and enable automated misuse.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests free text and image inputs extracted from the target captcha page context (e.g., TikTok “challenge text” in step 2 and DOM extraction in SadCaptcha reference), and that page/user-provided content can be outsider-authored.