8 docs tagged with "agent-safety"

Eight categories of agent risk, the confused deputy problem, severity matrices, and a Python risk assessment module.

Least privilege, reversibility preference, scope confirmation, and a Python minimal-footprint agent wrapper.

Indirect prompt injection attacks, real-world examples, detection and defense strategies, and a Python injection defense system.

Pre- and post-action guardrails, composable validators, denylist enforcement, rate limiting, and a complete Python guardrail pipeline.

Design human oversight that is meaningful, not performative - risk-based interruption, async approval queues, audit trails, and graduated autonomy.

Risk taxonomy, minimal footprint, prompt injection defense, guardrails, human oversight, sandboxing, and responsible deployment.

Safety principles, EU AI Act compliance, accountability chains, bias, privacy, red-teaming, and building a safety review process for autonomous agent systems.

Contain the blast radius of any agent failure - process isolation, Docker security hardening, network policy, E2B cloud sandboxes, and escape vector prevention.