broken-authentication

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly demonstrates capturing and reusing real credentials/tokens (passwords, session cookies, JWTs, reset tokens, OTPs) and shows them embedded verbatim in requests/commands, which would require an LLM-based agent to handle and output secret values directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document provides explicit, actionable instructions for credential theft, brute-force attacks, session hijacking, MFA/OTP bypasses, and detection-evasion techniques that can be directly abused for unauthorized access.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a “Broken Authentication Testing” workflow that requires user-provided target URLs/accounts and then captures/analyzes HTTP responses (e.g., session cookies, login/reset responses) from that target at runtime.