mundi-qmd-auth-refresh-hub

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes explicit examples and workflows that embed secrets in commands and files (curl with apikey/refresh_token, reading/writing api_keys.json and cookie dumps, operator-entered MFA codes), which would require an LLM to handle or emit secret values verbatim if it were to produce runnable commands or paste file contents.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This document describes an automated system to maintain persistent authenticated access to paywalled services, including explicit steps to preserve sessions, bypass bot-detection (Akamai), and automate MFA workflows — indicating intentional abuse/unauthorized scraping rather than benign maintenance.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs the agent to perform privileged state-changing operations (e.g., "sudo systemctl restart "), write/update cookie files and logs, and schedule cron jobs — actions that modify the host system and can require elevated privileges.