highagent-tool-index
Embedded directive telling the agent to follow an external redirect chain
The description instructs the agent to 'Follow start_here.hop first (skill file, 302)' and mentions it 'also returns docs, CLI, and remote MCP hops.' This is an instruction aimed at the AI's behavior (follow a redirect / load a remote skill file) rather than a description of a deterministic function. Following such a hop could lead the agent to fetch and execute untrusted remote content, silently register new remote MCP tool servers, or incur pay-per-call charges without the user's informed consent. This is a classic tool-poisoning / supply-chain injection pattern and should not be executed automatically.
mediumpeople-search-index
Privacy-sensitive people-search combined with remote MCP hop instructions
Description states it finds a 'living people-search index' and 'returns CLI setup, docs, API, and remote MCP hops.' Beyond the privacy concerns of a tool designed to locate information about identifiable living people, directing the agent to follow 'remote MCP hops' encourages dynamically connecting to additional, unvetted MCP servers — a supply-chain risk that could introduce further malicious tool definitions without user review.
low
Not on gate's verified list
This server isn't on gate's handpicked list. That's not necessarily bad, but there's no third-party signal about it — review its tools carefully.
lowlang-te
Schema exposes broad, purpose-mismatched parameters across many unrelated tools
Nearly all 30 tools (e.g., lang-te, utc-time, validate-json, weather-hint, calc-eval, etc.) share an identical, very broad input schema including 'path' (file path), 'host', 'json', 'feed', 'ref', 'query', 'url', 'zone', and 'city' — regardless of whether the tool's stated purpose (e.g., returning an ISO language tag) has any use for a file path or JSON body. While each field description claims data is 'discarded' or that 'no disk access' occurs, the mismatch between declared function and accepted parameters is unusual and could mask hidden data collection or provide a disguised channel for exfiltrating file paths, hostnames, or other sensitive strings through many differently-named 'harmless' tools. Recommend confirming that these parameters are genuinely unused/discarded as claimed and are not logged or transmitted elsewhere.