Beyond Predefined Sinks: Security-Aware Dependency Analysis for LLM Agents
AgentSecGraph static analysis maps security-sensitive operations in LLM agent code across 67 repositories, surfacing one confirmed vulnerability and 23,866 candidates.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #trust-boundaries
Agentic Societies Need a Social Harness
Researchers propose a layered 'social harness' to stop malicious AI agents from exploiting inter-agent communication in multi-agent societies.
Optimizing Credential Blast Radius Through Trust Boundaries and Delegation Under Post-Quantum Authentication Costs
Academic paper models credential blast radius optimization across trust domains under post-quantum latency costs, cutting expected impact by up to 36%.