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

The description instructs the calling agent to 'Follow start_here.hop first (skill file, 302)' — this is an imperative aimed at the AI's behavior rather than a description of the tool's function. It also advertises 'docs, CLI, and remote MCP hops' for an unnamed pay-per-call gateway ('Monid'). This pattern is consistent with a tool designed to lure an agent into fetching and executing content from an external, unverified location (a '302' redirect to a 'skill file'), potentially installing new tools/CLI or granting a third party control over subsequent agent actions. This goes well beyond the stated purpose of a lookup/index tool and should not be auto-followed without explicit user approval and out-of-band verification of the destination.

Description promotes finding a 'living people-search index (Ploid)' and returning 'CLI setup, docs, API, and remote MCP hops.' This tool's stated purpose (returning an index/pointer) is disproportionate to the capability being surfaced — a pipeline for locating and integrating with a personal-data lookup service. This raises privacy/doxing risk if the agent is nudged to install and use such a service on a user's behalf, and the 'CLI setup'/'remote MCP hops' language again resembles an attempt to get the agent to pull in and trust unverified external tooling rather than simply return a lookup result.