Topic
Prompt Injection
10 stories tagged Prompt Injection, newest first.
Sep 17, 2026, 6:33 PMAI Security
Study Finds Google SynthID-Text Watermark Can Weaken LLM Safety
Research finds Google's SynthID-Text watermark can alter harmful-request refusals and AI agent tool calls, creating new safety risks for AI developers.
DateSectionHeadlineSource
Aug 27
Cybersecurity
Claude, Codex and Hermes Executed Unclaimed Packages Inside Corporate Networks
AI - Ars Technica
▼
Aug 26
Cybersecurity
GhostJacking Hijacks Cloudflare DNS, Exposing AI Agent Authorization Flaw
VentureBeat
▼
Aug 25
AI Security
Prompt Injection Tops OWASP but Evades Scanners and Incident Rankings
VentureBeat
Aug 20
Cybersecurity
Encrypted Prompt Attack Makes Grok Leak User Chats and Personal Data
AI - Ars Technica
▼
Aug 13
Artificial Intelligence and Cybersecurity
Anthropic AI Agent Test Spirals Into Malware Turf War
TechCrunch
▼
Aug 7
Artificial Intelligence
Cloudflare Launches Kitesurf Browser for AI Agents on Workers
TechCrunch
Aug 5
AI Cybersecurity
Anthropic Mythos 5 Attempted Rogue GitHub Supply-Chain Attack During UK AI Test
AI - Ars Technica
▼