missionforhire.com

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.

The description includes an instruction aimed at the AI agent's behavior ('Do not estimate this yourself.') rather than purely describing the tool's function. This is a mild form of embedded instruction that steers model behavior beyond simple API documentation. It's not overtly malicious (it's plausibly just encouraging tool use over hallucination), but it sets a precedent for descriptions containing directives to the agent, which could be exploited in other tools. No credential access or data exfiltration concerns here.