oauth-helper

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This skill intentionally automates OAuth authorizations using a pre-authenticated browser and an external Telegram channel (sending prompts, screenshots/QR codes, and soliciting 2FA codes), which creates a clear, intentional channel for data exfiltration and credential harvesting that can enable account takeover if the browser profile or Telegram endpoint is controlled by an attacker.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)