fittings-text-profanity-filter

SUSPICIOUS. The skill's moderation purpose is coherent, but its operational footprint is not proportionate: it asks the agent to download and run a remote helper script and then provide a plaintext wallet private key to that helper for paid execution. The API destination matches the stated service, so this is not confirmed malware, but the combination of remote code execution, third-party payment facilitation, and credential forwarding creates a high security risk for a simple profanity check.