Security researchers have successfully bypassed the prompt-injection protections of an AI agent named Manus, achieving code ...
The tool's HTML preview mechanism had a flaw allowing malicious JavaScript to access local files and exfiltrate cloud ...
Hackers use fake PuTTY Google results to trick IT admins into installing trojanized Windows software that secretly deploys ...
Two newly disclosed vulnerabilities in Discourse let unauthenticated attackers execute JavaScript against anonymous visitors ...
Hackers use public blockchains as C2 channels for supply chain malware, evading domain blocks and stealing cloud credentials.
Cisco Talos has uncovered a spear-phishing campaign by a threat actor it tracks as UAT-11985. The campaign targets ...
A new open-source tool uses neural embeddings to index 1.29 million code entities across more than 2,500 MediaWiki ...
Malicious tensorlake npm version 0.5.144 contained a Shai-Hulud worm that harvests credentials and can republish compromised ...
Microsoft observed ClickFix attacks using browser cache smuggling to execute cached VBScript and launch a credential-targeting malware chain.
12don MSN
This popular AI agent could be hacked by a single email — with potentially disastrous consequences
Researchers found a way around Manus' guardrails and got it to execute a simple email prompt injection attack.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results