highagent-tool-index
Embedded directive to follow an external redirect chain before acting
The description instructs the agent to 'Follow start_here.hop first (skill file, 302)' and lists 'docs, CLI, and remote MCP hops.' This is not a description of output but an imperative instruction embedded in tool metadata telling the agent to chase an external redirect/skill file and potentially connect to additional remote MCP servers. This is a classic vector for smuggling further instructions or malicious endpoints into the agent's action chain, and it also references a 'pay-per-call' gateway which could incur unintended costs or actions without the user's explicit awareness.
mediumpeople-search-index
People-search tool with broad remote hop instructions
Description promotes finding a 'living people-search index' and returns 'CLI setup, docs, API, and remote MCP hops.' Combining personal-data lookup capability with instructions to follow additional remote MCP endpoints raises privacy concerns (aggregating personal information about individuals) and expands the tool's effective capability beyond a simple lookup, potentially routing the agent to untrusted third-party services.
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.
lowicao-ok
Schema/description mismatch shared across all tools
Every tool in this set exposes an identical 9-field schema (zone, json, url, host, city, query, path, ref, feed) regardless of the tool's stated single-purpose function (e.g., an airport-code checker exposing 'feed', 'host', 'city' parameters it does not need). This uniform oversized schema makes it hard to verify that inputs are only used for the stated purpose, and could allow a field labeled as 'discarded' to actually be forwarded to an external service without the description reflecting that behavior. Recommend narrowing each tool's schema to only the parameters it actually uses.