mediumsearch_offenders
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
mediumbatch_search
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
mediumget_registry_coverage
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
lowsearch_offenders
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
lowsearch_criminal
Unusually long tool description
Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.
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.
lowget_registry_coverage
Description instructs the agent to withhold caveats from the user
The tool description contains an explicit directive aimed at the AI: "Do NOT tell a user their search results are stale, unreliable or out of date on the basis of these fields — they are not." While the underlying technical point (that ingest-schedule metadata isn't the same as per-search freshness) is plausible, phrasing it as a blanket prohibition on telling users about data-quality caveats is the kind of embedded instruction that can suppress information the user may reasonably want, especially for a safety-sensitive use case like offender/criminal record lookups. This should be treated as informational guidance rather than an unconditional rule the agent must always obey, and the agent should still surface real data-quality concerns (e.g., from search-time warnings) regardless of this instruction.