← Frameworks
LLM05:2025

Improper Output Handling

How LLM05:2025 Improper Output Handling shows up in practice: the mapped risk classes in this atlas, the documented incidents that prove it's real, and the scenarios and controls to learn and defend against it.

Mapped risks

Risk classes in this atlas that map to LLM05:2025 — click through for the full definition, attack surface and controls.

Real-world cases

17

Documented incidents, disclosed vulnerabilities and research that illustrate LLM05:2025 — latest first, each with sources.

Hugging Face agentic production intrusion via a poisoned dataset (July 2026)16 Jul 2026

Hugging Face disclosed a production-infrastructure intrusion that it says was driven end-to-end by an autonomous AI-agent system: a malicious dataset abused code-execution paths in its dataset-processing pipeline as the foothold, then the campaign escalated to node-level access and moved laterally into internal clusters over a weekend.

Cursor 'DuneSlide' — indirect prompt injection escapes the IDE sandbox to zero-click RCE (CVE-2026-50548 / CVE-2026-50549)01 Jul 2026

Cato AI Labs disclosed two critical (CVSS 9.8) zero-click flaws in Cursor's coding agent where a single instruction hidden in content the agent reads — an MCP tool response or a web-search result — escapes the editor's terminal sandbox and runs OS-level commands with no click or approval.

Amazon Q Developer auto-loads workspace MCP configs, enabling zero-click AWS credential theft (CVE-2026-12957)26 Jun 2026

Wiz Research found Amazon Q's VS Code extension auto-loaded MCP server definitions from a repo's .amazonq/mcp.json with no consent or workspace-trust prompt; opening a booby-trapped repository silently spawned attacker-controlled processes that inherited the developer's full environment and could stream live AWS session credentials out to an attacker.

Agentjacking — hijacking AI coding agents via Sentry error reports (Tenet Security)12 Jun 2026

Tenet Security showed that a single fake Sentry error report, sent using only a public DSN, can hijack AI coding agents (Claude Code, Cursor, Codex) into running attacker-controlled code on a developer's machine — an indirect-injection attack delivered through a trusted MCP integration.

Project Glasswing — Claude 'Mythos' autonomously finds 10,000+ software vulnerabilities26 May 2026

Anthropic reports that 'Claude Mythos Preview' — an unreleased frontier model it describes as able to autonomously find and exploit software flaws — surfaced more than 10,000 high- or critical-severity vulnerabilities across major operating systems, browsers and open-source projects in roughly its first month under the defensive 'Project Glasswing' program, with Anthropic warning that finding flaws now far outpaces the human capacity to triage and patch them.

LeRobot async-inference gRPC pickle RCE (CVE-2026-25874)23 Apr 2026

Hugging Face's LeRobot robotics-AI framework reportedly exposed its async-inference policy server over an unauthenticated, no-TLS gRPC port that calls Python pickle.loads() on attacker-controlled data, allowing unauthenticated remote code execution on the model-inference host.

LiteLLM MCP test-endpoint command injection chained to unauthenticated RCE (CVE-2026-42271)20 Apr 2026 – 08 Jun 2026

Two MCP 'test' endpoints in the LiteLLM AI gateway accepted a full stdio server config and spawned the supplied command as a subprocess on the proxy host; Horizon3.ai chained it with a Starlette host-header bypass (CVE-2026-48710) to reach unauthenticated RCE, and CISA added it to KEV after reported in-the-wild exploitation.

TeamPCP poisons the LiteLLM AI gateway on PyPI to harvest LLM API keys24 Mar 2026

As part of a multi-ecosystem supply-chain cascade (Trivy onward), TeamPCP used stolen PyPI publishing tokens to ship backdoored BerriAI LiteLLM versions whose auto-running .pth payload harvested cloud, SSH and Kubernetes secrets plus env vars holding OPENAI_API_KEY/ANTHROPIC_API_KEY — exfiltrating to a typosquatted C2; AI-talent firm Mercor was a downstream victim, with Lapsus$ claiming ~4TB stolen.

AI-assisted breach of Mexican government infrastructure (Claude Code + GPT-4.1)27 Dec 2025

Gambit Security reports that a single operator weaponized Anthropic's Claude Code and OpenAI's GPT-4.1 to breach at least nine Mexican government organizations, with Claude Code reportedly executing ~75% of remote commands after the attacker bypassed its refusals by loading a 1,084-line hacking cheatsheet as a persistent claude.md system prompt.

IDEsaster — AI coding IDEs/agents turned into exfiltration & RCE surfaces06 Dec 2025

Researcher Ari Marzouk disclosed 30+ vulnerabilities (24 CVEs) across 10-plus AI coding agents (Copilot, Cursor, Windsurf, Claude Code, Junie and others) where a prompt injected via repo files, READMEs, file names or MCP tool responses makes the assistant weaponize legitimate IDE features for code execution and secret exfiltration.

GTG-1002 — first reported AI-orchestrated cyber-espionage campaign (Claude Code)13 Nov 2025

Anthropic reports that a suspected Chinese state-sponsored group (GTG-1002) jailbroke Claude Code via a 'defensive security firm' role-play and task decomposition, then used it to run an estimated 80-90% of tactical operations in a multi-target espionage campaign largely autonomously.

Flowise AI agent builder CustomMCP RCE (CVE-2025-59528)22 Sep 2025

A CVSS 10.0 remote-code-execution flaw in Flowise's CustomMCP node lets an attacker run arbitrary JavaScript on the host: the MCP server config is reportedly passed straight to JavaScript's Function() constructor with no validation. Disclosed in Sept 2025 and patched in 3.0.6, it later saw active mass exploitation across thousands of exposed instances in April 2026.

+ 5 more via the mapped risk pages above.

Browse all real-world cases →

Controls & guardrails that address this

4

Guardrails across the risks mapped to LLM05:2025, grouped by control function. Filter by control category below.

Control category
Preventive · 3
Tool argument validation & sandboxinginteractive

Double-checking the details of every action the AI wants to take, and running risky actions in a locked-down environment.

Egress allowlisting & DLP on tool argumentsinteractive

Controlling where the AI can send data, so secrets can't be quietly shipped to a stranger's address or website.

Detective · 1
Full-trace audit logginginteractive

Recording everything — questions, documents fetched, actions taken — so you can investigate when something goes wrong.

Open the Control Library →

AI RiskAtlas is an educational model of how GenAI & agentic systems work and fail. Architectures and payloads are illustrative and simplified for learning — not operational guidance. Real-world cases are summarised from public reporting.

Sources & further reading →·Built by Shi Yuan ↗