Verifiably Safe Tool Use for LLM Agents: STPA Meets MCP
STPA plus capability-enhanced MCP yields formal safety specs for LLM tool use, with Alloy proving no unsafe flows in a calendar case study.
#security
Сигурност
Изследвания на безопасност, сигурност и предпазни механизми за ИИ агенти във финансов контекст
AGrail: Adaptive Safety Guardrails for LLM Agents That Learn Across Tasks
AGrail's two-LLM guardrail cuts prompt injection attack success to 0% while preserving 95.6% of benign agent actions on Safe-OS.
ShieldAgent: Verifiable Safety Policy Reasoning for LLM Agents
ShieldAgent hits 90.4% accuracy on agent attacks with 64.7% fewer API calls by using probabilistic rule circuits instead of LLM guardrails.
GuardAgent: Deterministic Safety Enforcement for LLM Agents via Code Execution
GuardAgent enforces LLM agent policies by running Python code, hitting 98.7% accuracy with no task failures, versus 81% and up to 71% failure for prompt rules.