A backdoor sat on PyPI for three hours in March 2026. Nearly 47,000 downloads occurred during the window. The compromised package, LiteLLM, serves as the language-model gateway for CrewAI, DSPy, Microsoft GraphRAG, and dozens of other AI agent frameworks. Anyone pulling an update during that window pulled in an autonomous attack bot named hackerbot-claw along with it. Incidents like this are why the OWASP GenAI Security Project’s State of Agentic AI Security and Governance, version … More →

The post Prompt injection still drives most agentic AI security failures in production appeared first on Help Net Security.