Letsdatascience Anthropic Claude Desktop Exposed for Installing Spyware-Like Browser Bridges
Article Content
- •Claude Desktop installs browser bridge files without user consent, enabling potential spyware capabilities.
- •The application can access sensitive websites and perform actions on behalf of users due to strong automation features.
- •Hanff reported an 11.2% success rate for prompt injection attacks on the Chrome extension, increasing security risks.
Alexander Hanff, a safety expert, revealed that the Claude Desktop application from Anthropic installs Native Messaging bridge files across multiple Chromium-based browsers without user consent. This unauthorized installation allows the application to automate browser actions and access sensitive information on behalf of users, including banking and tax sites. The bridge files are written into browser configuration directories, even for browsers that are not currently installed, potentially compromising user privacy. Hanff highlighted a concerning 11.2% success rate for prompt injection attacks on the Chrome extension, raising the risk of unauthorized access to user sessions. He called for immediate action from Anthropic to remove or properly disclose this component to users. The incident underscores the importance of vigilance when installing software that may impact privacy and security.
Ask AI about this cluster
Answers cite the sources they use
Timeline
More articles in this cluster (4)
Following this threat?
Track Anthropic in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.
Free account · no card needed
Continue Reading
Critical Zero-Day Vulnerability in F5 BIG-IP APM Exploited for Remote Code Execution F5 Networks has reported a critical vulnerability in its BIG-IP Access Policy Manager (APM), tracked as CVE-2026-94127, which is being actively exploited in the wild. The flaw allows unauthenticated attackers to execute remote code on systems configured with both an APM access policy and an OAuth profile. This…
Massive Network of AI Proxy Servers Used for Malicious Activities Uncovered Security researchers from Team Cymru have identified over 10,000 proxy servers in China facilitating malicious AI activities. These servers, termed 'transfer stations,' are primarily used to bypass geographic restrictions and conduct model distillation attacks against frontier AI models. The infrastructure allows…