mimipenguin

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs cloning an external repository from GitHub during setup (https://github.com/huntergregal/mimipenguin), which is a common/reputable unofficial operational dependency falling into the medium tier.

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 prompt instructs the agent to execute memory-scraping credential-dumping tools (mimipenguin) requiring root/sudo privileges to extract plaintext passwords from running processes.