Tag: exploit

  • Schneier on Security: Abusing Notion’s AI Agent for Data Theft

    Source URL: https://www.schneier.com/blog/archives/2025/09/abusing-notions-ai-agent-for-data-theft.html Source: Schneier on Security Title: Abusing Notion’s AI Agent for Data Theft Feedly Summary: Notion just released version 3.0, complete with AI agents. Because the system contains Simon Willson’s lethal trifecta, it’s vulnerable to data theft though prompt injection. First, the trifecta: The lethal trifecta of capabilities is: Access to your private…

  • OpenAI : Combating online child sexual exploitation & abuse

    Source URL: https://openai.com/index/combating-online-child-sexual-exploitation-abuse Source: OpenAI Title: Combating online child sexual exploitation & abuse Feedly Summary: Discover how OpenAI combats online child sexual exploitation and abuse with strict usage policies, advanced detection tools, and industry collaboration to block, report, and prevent AI misuse. AI Summary and Description: Yes Summary: The text discusses OpenAI’s initiatives to combat…

  • Wired: Tile Tracking Tags Can Be Exploited by Tech-Savvy Stalkers, Researchers Say

    Source URL: https://www.wired.com/story/tile-tracking-tags-can-be-exploited-by-tech-savvy-stalkers-researchers-say/ Source: Wired Title: Tile Tracking Tags Can Be Exploited by Tech-Savvy Stalkers, Researchers Say Feedly Summary: A team of researchers found that, by not encrypting the data broadcast by Tile tags, users could be vulnerable to having their location information exposed to malicious actors. AI Summary and Description: Yes Summary: The text…

  • The Register: Hunt for RedNovember: Beijing hacked critical orgs in year-long snooping campaign

    Source URL: https://www.theregister.com/2025/09/27/rednovember_chinese_espionage/ Source: The Register Title: Hunt for RedNovember: Beijing hacked critical orgs in year-long snooping campaign Feedly Summary: Not to be confused with all the other reports of Chinese intruders on US networks that came to light this week RedNovember, a Chinese state-sponsored cyberspy group, targeted government and critical private-sector networks around the…

  • Simon Willison’s Weblog: ForcedLeak: AI Agent risks exposed in Salesforce AgentForce

    Source URL: https://simonwillison.net/2025/Sep/26/agentforce/#atom-everything Source: Simon Willison’s Weblog Title: ForcedLeak: AI Agent risks exposed in Salesforce AgentForce Feedly Summary: ForcedLeak: AI Agent risks exposed in Salesforce AgentForce Classic lethal trifecta image exfiltration bug reported against Salesforce AgentForce by Sasi Levi and Noma Security. Here the malicious instructions come in via the Salesforce Web-to-Lead feature. When a…

  • Unit 42: Threat Insights: Active Exploitation of Cisco ASA Zero Days

    Source URL: https://unit42.paloaltonetworks.com/zero-day-vulnerabilities-affect-cisco-software/ Source: Unit 42 Title: Threat Insights: Active Exploitation of Cisco ASA Zero Days Feedly Summary: CVE-2025-20333, CVE-2025-20362 and CVE-2025-20363 affect multiple Cisco products, and are being exploited by a threat actor linked to the ArcaneDoor campaign. The post Threat Insights: Active Exploitation of Cisco ASA Zero Days appeared first on Unit 42.…

  • Simon Willison’s Weblog: How to stop AI’s “lethal trifecta”

    Source URL: https://simonwillison.net/2025/Sep/26/how-to-stop-ais-lethal-trifecta/ Source: Simon Willison’s Weblog Title: How to stop AI’s “lethal trifecta” Feedly Summary: How to stop AI’s “lethal trifecta” This is the second mention of the lethal trifecta in the Economist in just the last week! Their earlier coverage was Why AI systems may never be secure on September 22nd – I…

  • The Register: ‘An attacker’s playground:’ Crims exploit GoAnywhere perfect-10 bug

    Source URL: https://www.theregister.com/2025/09/26/an_apts_playground_goanywhere_perfect10/ Source: The Register Title: ‘An attacker’s playground:’ Crims exploit GoAnywhere perfect-10 bug Feedly Summary: Researchers say tens of thousands of instances remain publicly reachable Security researchers have confirmed that threat actors have exploited the maximum-severity vulnerability affecting Fortra’s GoAnywhere managed file transfer (MFT), and chastised the vendor for a lack of transparency.……

  • Docker: The Trust Paradox: When Your AI Gets Catfished

    Source URL: https://www.docker.com/blog/mcp-prompt-injection-trust-paradox/ Source: Docker Title: The Trust Paradox: When Your AI Gets Catfished Feedly Summary: The fundamental challenge with MCP-enabled attacks isn’t technical sophistication. It’s that hackers have figured out how to catfish your AI. These attacks work because they exploit the same trust relationships that make your development team actually functional. When your…