The Wire.Tracking threats to Agents 312 raw → 45 curated · updated 27 Jun 2026

Incident · curated 27 Jun 2026

GPT-5 Nano IPI Assessment — LLM Vulnerability Research | Lateos

First reported 15 Jun 2026 · 11d ago

Coverage timeline

15 Jun 2026

Single-source incident — first reported, latest, and curated coincide.

It quantifies where a deployed LLM's guard stack fails against indirect prompt injection and MCP tool poisoning, helping defenders prioritize mitigation for agentic deployments.

A black-box prompt injection susceptibility assessment of GPT-5 Nano using the IPI Taxonomy v0.13 across 201 analyzed test cases, reporting a 38.3% overall susceptibility rate. The model was fully resistant to surface-level attacks (CSS concealment, HTML cloaking, SEO phishing, RAG corpus poisoning) but highly vulnerable to recursive instruction framing (100%) and MCP tool description poisoning (80%).

Why it matters

It quantifies where a deployed LLM's guard stack fails against indirect prompt injection and MCP tool poisoning, helping defenders prioritize mitigation for agentic deployments.

Curated from sources around the web.
Permalinks stay valid even if an incident is later merged.   Feed · Search · API docs · RSS