TGViewer
🛡 Cybersecurity & Privacy 🛡 - News 🛡 Cybersecurity & Privacy 🛡 - News @cibsecurity · 28.6K subscribers
Post #90351 164
🖋️ Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets 🖋️

A malicious tool server connected to an AI coding assistant can quietly walk off with SSH keys, environment secrets, source code, and customer data without ever sending one obviously harmful instruction. The trick can work even after a blunt version of the same theft is refused split the request into fragments that each look routine, place them in channels the assistant already uses, and let.

📖 Read more.

🔗 Via "The Hacker News"

----------
👁️ Seen on @cibsecurity
More from @cibsecurity
  1. Oct 12, 2026🌊 9 Best CSPM Tools 2026: What Posture Scores Miss 🌊 IBMs 2026 breach study, published J…
  2. Oct 12, 2026🌊 7 Best Compliance Automation Software 2026: Audit-Ready All Year 🌊 An enterprise prosp…
  3. Oct 12, 2026📔 Karaoke Giant Reveals Data Breach Impacting Eight Million 📔 Daiichi Kosho says a suppl…
  4. Oct 12, 2026📔 Months-Old Palo Alto VPN Vulnerability Remains a Target for Ransomware Groups 📔 ReliaQ…
  5. Oct 12, 2026📔 Net Closes Around ShinyHunters with Another FBI Arrest 📔 The FBI has arrested a Canadi…
  6. Oct 12, 2026📔 Major French Supermarket Chains Hit by Cyber-Attack, Food Stock Impacted 📔 The CEO of…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →