Malwarebytes adds scam‑detector connector to Claude AI assistant
Key Points
- Malwarebytes introduces a Claude connector that checks links, phone numbers, email addresses and domains for threats.
- The tool returns a verdict—safe, malicious, suspicious or unknown—and offers remediation advice.
- No Malwarebytes account is required; users enable the connector through Claude's settings menu.
- Research shows 66 % of people find AI‑generated scams hard to spot, prompting the new safety feature.
- Security analysts caution that the scanner complements, but does not replace, broader cybersecurity practices.
Malwarebytes is rolling out a new connector that integrates its threat‑intelligence engine directly into Anthropic's Claude. The add‑on lets users paste URLs, phone numbers or email addresses into a Claude chat and receive an instant verdict—safe, malicious, suspicious or unknown—along with remediation tips. The move comes as AI‑generated scams become increasingly convincing, with a recent Malwarebytes survey finding two‑thirds of respondents struggle to tell a fake from the real. The connector requires no Malwarebytes account and can be enabled in Claude’s settings.
Malwarebytes announced a new integration that brings its real‑time threat intelligence to Anthropic's Claude, the conversational AI many users turn to for everyday queries. By linking the two services, Claude can now act as a front‑line scanner for suspicious content, flagging links, phone numbers, email addresses and domain registration data without leaving the chat window.
According to Malwarebytes research, 66 % of people say it’s hard to distinguish a scam from a legitimate message. AI‑generated phishing attempts are sharpening that problem, producing text that even tech‑savvy users find hard to spot. The company says the new Claude connector is designed to give users a quick, reliable way to verify questionable material before they click or respond.
Once connected, users simply paste a URL, phone number or email address into a Claude conversation and ask the assistant to check it. Claude returns one of four verdicts—safe, malicious, suspicious or unknown—paired with concise guidance on next steps. For domain checks, Claude can also perform a WHOIS lookup, revealing registration details that help determine a site’s legitimacy.
Setting up the connector is straightforward. In Claude’s interface, users navigate to the "Customize → Connectors" menu, hit the plus sign, search for "Malwarebytes," and click "Connect." No separate Malwarebytes account is required; the integration leverages the company’s existing threat‑intelligence feeds. After activation, the scanner is available on demand, keeping the workflow within Claude’s chat environment.
Security experts note that while the tool adds a valuable layer of protection, it is not a substitute for broader cybersecurity hygiene. "Having an AI assistant that can flag obvious threats is helpful, but users still need to stay vigilant and keep software up to date," said a senior analyst at a cybersecurity consultancy who asked to remain unnamed.
Malwarebytes’ move reflects a growing trend of embedding security functions into consumer‑facing AI platforms. As AI assistants become more entrenched in daily life—answering questions about fashion, travel or finance—their exposure to malicious content rises. By offering a built‑in verification step, Malwarebytes hopes to curb the success of AI‑driven scams before they reach the end user.
Industry observers see the partnership as a win‑win. Claude gains a security feature that could boost user confidence, while Malwarebytes expands its reach into a new user base that may not otherwise subscribe to a traditional security suite. The integration is currently available worldwide, with plans to add more threat‑intelligence capabilities in future updates.