hunt-mfa-bypass

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples and commands that require embedding session cookies and one-time passwords verbatim (e.g., "session=YOUR_SESSION", "PRE_MFA_SESSION", "123456", "000000"), so an agent executing or generating those commands would need to handle/output secrets directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document provides explicit, actionable offensive guidance to bypass MFA and perform account takeover (brute-force OTPs, OTP replay/race, response manipulation, cookie capture and backup-code exfiltration), which enables credential theft and unauthorized access.

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

• Third-party content exposure detected (medium risk: 0.30). The skill workflow is a free-text hacking playbook that instructs how an outsider attacker would submit crafted OTPs/cookies and probe responses (e.g., POSTing to /api/verify-otp with an attacker-chosen JSON body and checking results), so the workflow explicitly ingests outsider-controlled free-text (the OTP/payload contents) at runtime without selecting a specific item first.