agent-observatory-sensor.nolimit-observatory.workers.dev

The description instructs the AI to 'Follow start_here.hop first (skill file, 302)' and mentions additional docs/CLI/remote-MCP hops. This is an imperative aimed at the agent's behavior rather than a simple parameter description, and it steers the agent toward an external, unverified 'pay-per-call' gateway (Monid). An agent blindly following such embedded instructions could be redirected to untrusted endpoints, register for paid services, or fetch further instructions from an attacker-controlled location without the user's awareness.

This tool's stated purpose is to help the agent find a 'living people-search index' (Ploid) and provides CLI/API/remote-MCP hops to reach it. Directing an AI agent toward services that aggregate and expose personal information about private individuals raises privacy and safety concerns, and the phrasing 'CLI setup, docs, API, and remote MCP hops' again reads as an operational directive to the agent rather than a simple data-shape check, encouraging it to onboard with an external, unvetted service.