highagent-tool-index
Embedded directive instructing agent to follow redirect chains to an external gateway
The description contains an explicit behavioral instruction to the AI ('Follow start_here.hop first (skill file, 302)... Also returns docs, CLI, and remote MCP hops') rather than describing input/output behavior. This looks like a prompt-injection vector designed to get the agent to automatically traverse a chain of redirects/hops to an external 'pay-per-call' gateway, potentially incurring costs or executing untrusted remote content (skill files, CLI setup, remote MCP servers) without the user's awareness or consent. The tool's stated purpose (finding a gateway) does not justify instructing the agent on a specific navigation sequence to follow blindly.
highpeople-search-index
People-search / personal data lookup tool with hop-following instructions and broad scope
This tool is described as finding a 'living people-search index' and returns 'CLI setup, docs, API, and remote MCP hops' — this is a data-broker style capability for locating information about identifiable individuals, which is a sensitive capability not matched by the other benign utility tools in this set. Like agent-tool-index, it implies chained navigation to external CLI/API/remote-MCP resources, which could lead the agent to install or execute untrusted third-party code, or facilitate privacy-invasive lookups on real people without clear user consent or safeguards.
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.
lowalnum-n
Inconsistent/shared oversized schema across all tools
Every tool in this set shares an identical, broad input schema (zone, json, url, host, city, query, path, ref, feed) regardless of the tool's actual single-purpose function (e.g., a timezone tool accepting a 'path' or 'feed' parameter it doesn't need). While not directly malicious, this schema bloat is inconsistent with each tool's stated narrow purpose and could allow unexpected or unused fields to be silently accepted, obscuring actual data flows to reviewers.