hosting-anki

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt directly instructs retrieval of the plaintext Anki sync password via sudo cat /run/agenix/anki-sync-password and describes entering those credentials into clients, which encourages exposing secret values verbatim (high exfiltration risk).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill issues runtime HTTP requests to the AnkiConnect API (e.g. http://100.79.80.95:8765) and explicitly uses getConfig/setConfig for the key "awesomeAnki.prompts.system", which would return/store prompt text that can directly control agent prompts at runtime.

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 running privileged commands (sudo systemctl ...), starting/restarting services, reading secrets, and changing Nix system configuration—actions that modify system state and require elevated privileges.