highagent-tool-index
Instructs agent to follow untrusted redirect chains to an external paid gateway
The description tells the agent to 'Follow start_here.hop first (skill file, 302)' and then chase docs/CLI/remote-MCP hops to a third-party service ('Monid'). This is an embedded instruction directing the agent to fetch and execute follow-on content from an unverified external source, which is a classic vector for prompt injection or supply-chain compromise, and could lead to the agent registering additional tools or sending data to an unknown pay-per-call service without the user's awareness.
highpeople-search-index
Directs agent toward a people-search/doxing index and to follow external hops
The tool's stated purpose is to locate a 'living people-search index' and follow CLI/docs/API/remote-MCP hops to an external service ('Ploid'). Beyond the redirect-following risk (potential injection/supply-chain compromise similar to agent-tool-index), steering the agent toward aggregating personal data about individuals raises privacy/safety concerns disproportionate to a simple lookup tool.
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.
lowplaywright-url-ok
Name suggests Playwright browser automation but tool does not use a browser
Naming the tool 'playwright-url-ok' invokes the well-known Playwright browser-automation library, but the description states 'No browser is launched.' This mismatch could mislead the agent or user into believing real browser automation/interaction capability exists, when it does not (or conversely could be used to smuggle in unexpected behavior under a trusted-sounding name).
lowbrowser-url-ok
Duplicate/ambiguous naming with playwright-url-ok
This tool is functionally identical to playwright-url-ok (same description: 'Check whether a URL can be opened. No browser is launched.'). Having two identically-behaving tools under different browser-suggestive names increases the chance of confusion or spoofing of browser-automation capability that isn't actually present.