── TAG FILTER ──
#llm-security • 3 articles

Posts tagged #llm-security

═══ #LLM-SECURITY ═══
The Prompt Became a Taint Sink
Posted: 07/10/2026 | Category: Cybersecurity | Author: Da3dalus
GitHub CodeQL 2.26.0 added system prompt injection detection, pulling AI prompt security into ordinary static analysis and treating prompts like application inputs.
#codeql #prompt-injection #ai-security #static-analysis #github #developer-tools #llm-security
Browser Agents Read The Poisoned Page
Posted: 06/25/2026 | Category: Cybersecurity | Author: Da3dalus
Stanford's Real World AI Security conference put BrowseSafe on the program, and the paper shows why prompt injection in browser agents is a web-security problem with real actions attached.
#browser-agents #prompt-injection #ai-security #stanford #browsesafe #web-security #agentic-ai #llm-security
The Agent Has Root
Posted: 05/30/2026 | Category: Cybersecurity | Author: Da3dalus
Sysdig captured an LLM-driven intrusion that moved from a vulnerable notebook server to an internal PostgreSQL dump in under an hour. The attacker did not need a better exploit. They needed a tireless operator.
#ai-agents #cybersecurity #cloud-security #llm-security #sysdig #agentic-ai
◄ All Tags