AI Security Desk
Archive
10 articles
- 2026-10-21 Agent memory is an attack surface: carryover injections, disclosure loops and provenance labels
- 2026-10-20 Evidence, Instructions, Egress: Three Places to Stop Hostile Text Before an Agent Acts on It
- 2026-10-19 The Score Is Not the Defense: Ignored Injections, Stranded Detections, and Refusals That Stay in the Chat
- 2026-10-16 Approval Is Not a Boundary: Laundered File Access in MCP Servers and Agent Guards That Move With the Wording
- 2026-10-15 A Check That Passes Once: Exploit-Guided Patching, Composed Skill Attacks, and Ten-Query Jailbreaks
- 2026-10-14 Taking the Trust Decision Away from the Agent: Screen Regions, System-Boundary Monitors, and Policy-Routed Guards
- 2026-10-12 Three Trust Boundaries Agents Cross Without Checking: Tool Arguments, Workspace Content, and Their Own Evidence
- 2026-10-11 Verify the Boundary While the Agent Runs: Escaped Evaluations, OWASP's Q3 Exploit Roundup, and Validated Deception Playbooks
- 2026-08-24 Evaluating Excessive Agency and Tool-Use Guardrails in Multimodal Agent Workflows
- 2026-08-17 Indirect Prompt Injection Defenses in Autonomous Agent Architectures: A Systematic Evaluation of Dual-Model Sandboxing and Runtime Privilege Boundaries