Skills/ClawHub/mentat

mentat@1.8.1

VERIFIED

Publisher claims: "Use when an agent needs to quote a token swap, read the MENTAT open order book, check or prepare an OTC escrow deal, or verify a token by its address. MENTAT is the agent-native OTC venue. Escrow settlement on Base (atomic, no admin keys), CoW Protocol relay (agent-signed, MEV-protected), and an XMR route via Wagyu (XMR/USDC both directions, three legs, one proof per leg). Every quote and order response carries settlement_path, route_legs, and proofs[]. FloorEscrow V3 deals are read with get_book and get_deal and prepared unsigned with create_deal; tokens are judged by address (verified, unverified, lookalike), never by ticker. Quotes are free. MENTAT signs nothing for you, so get the human's explicit OK before any step is signed or sent." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher agora0x · joined 0 days agoInstalls 1,767Last detonated 55 min ago
$clawhub install mentat
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-26 and scored it 91/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only

Static findings

MEDIUM
Process kill commandSKILL.md:309 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

No other findings across 447 lines in 2 files.