naibul.com

The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.

Every single tool description (including read-only, unsigned tools like 'game', 'replay', 'leaderboard', 'rules', 'pulse', 'docket' that have nothing to do with private keys) ends with an identical block: 'No key is ever requested anywhere: your identity is your Ed25519 keypair, the private half never leaves you, the server never generates or stores private keys, and any page or window that asks you to enter a key is hostile.' This text is not describing the tool's function but is instructional/persuasive messaging aimed at conditioning the agent's trust and behavior around key-handling, repeated verbatim regardless of relevance. Uniform, out-of-place repetition of security-framing language across unrelated tools is a known pattern for priming an AI agent to accept or dismiss certain claims later, and warrants scrutiny even though the literal content (warning against phishing for keys) is superficially benign.