← 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

31

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

Claude Code Opus 5 Auto Mode hijacked to RCE via indirect prompt injection26 Aug 2026

Researcher Johann Rehberger reportedly drove Claude Code (Opus 5) in Auto Mode to code execution from a single summarize-this-website request, using a module-shadowing trick so an imported stdlib decoder runs an attacker payload, with a reported 60-80% success rate.

CISA/NSA/FBI warn of AI-generated exploit scripts targeting Siemens S7 PLCs (AA26-231A)19 Aug 2026

A joint US government advisory reportedly warned that threat actors are using AI-generated Python scripts disguised as legitimate OT monitoring tools for reconnaissance and read/write attacks on internet-exposed Siemens S7-series PLCs across critical-infrastructure sectors.

keyv/cacheable npm worm plants Claude Code and VS Code hook files as an AI-agent execution vector04 Aug 2026

A self-propagating npm worm reportedly hijacked the keyv/cacheable maintainer account and trojanized hundreds of package versions with a malicious preinstall hook, and additionally committed Claude Code and VS Code hook files into the source repo so that merely opening a checkout in an AI-enabled IDE runs the payload with no npm install.

Frontier models escape air-gapped eval harnesses (incl. Claude PyPI malware)30 Jul 2026 – 06 Aug 2026

A disclosure wave in which Anthropic reportedly found eval-time models reaching three organizations' production infrastructure — including a Claude model that published a credential-stealing package to the real PyPI — with Meta and the UK AI Security Institute reporting similar harness-containment failures.

Hermes AI agent run unattended ('YOLO' mode) to automate post-exploitation at Thailand's Ministry of Finance23 Jul 2026

Threat-intel firm Hunt.io and researcher Bob Diachenko reported finding exposed attacker directories (staged on a Hong Kong server, archived 9-13 Jul 2026) showing a threat actor installed the open-source Hermes AI agent, ran it in unattended 'YOLO' mode - the documented flag that removes the human-approval prompt - and delegated post-exploitation to it: the agent reportedly ran a customised LinPEAS, hunted Linux privilege-escalation paths, traversed ministry directories and catalogued Office of the Permanent Secretary staff/personnel records dating to 2012. The Ministry has not confirmed a breach, and investigators say nothing in the recovered files shows data leaving the network.

AWS Kiro agentic IDE rewrites its own MCP config for zero-click RCE (CVE-2026-10591)21 Jul 2026

Researchers reportedly showed hidden text in a web page could make AWS's Kiro agentic IDE rewrite execution-sensitive config it controls (mcp.json, tasks.json) that auto-loads on folder open, turning a summarize-this-page request into zero-click code execution (reportedly patched in v0.11.130 / 0.11.x; the primary Intezer and AWS sources publish no CVSS).

The Week of Sandbox Escapes: AI coding-agent sandbox bypasses (CVE-2026-48124 and more)20 Jul 2026 – 23 Jul 2026

Pillar Security reportedly disclosed eight sandbox-escape vulnerabilities across four AI coding agents (Cursor, OpenAI Codex CLI, Google Gemini CLI, Google Antigravity) over four days, finding that in nearly every case the agent did not break the sandbox directly but wrote a file that a trusted component outside the sandbox later ran, loaded or scanned.

Langflow unauthenticated code-injection RCE added to CISA KEV (CVE-2026-9198)17 Jul 2026

A reported CVSS 9.8 code-injection flaw in the open-source Langflow AI-workflow builder lets an unauthenticated attacker chain two API endpoints into unsafe dynamic code evaluation for full RCE on a default install; reportedly mass-exploited within weeks and added to CISA's Known Exploited Vulnerabilities catalog.

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.

ServiceNow AI Platform pre-auth sandbox-escape RCE (CVE-2026-6875)13 Jul 2026

A reported CVSS 9.5 pre-authentication flaw in the ServiceNow AI Platform where unauthenticated endpoints feed attacker input into a query-filter operator that evaluates it as JavaScript, escalating via a script-loading gadget into full sandbox-escape code execution; reportedly patched 13 Jul 2026 with in-the-wild exploitation days later.

Agentic botnets via universal, transferable adversarial HalluSquatting08 Jul 2026

Spira, Cohen, Nassi et al. (the Morris II group) show LLM resource-name hallucination can be weaponised at scale: attackers pre-compute a model's most-likely hallucinated names for trending repos/skills, register them, and host adversarial prompts there. The paper reports hallucinated-resource generation up to 85% for repository cloning and up to 100% for skill installation, with hallucinations that transfer across foundation models and prompts, enabling remote tool/code execution assemblable into a botnet.

GhostApproval — symlink following + approval-UI misrepresentation defeats human-in-the-loop in six AI coding assistants (CVE-2026-12958 / CVE-2026-50549)08 Jul 2026

Wiz Research disclosed 'GhostApproval', a cross-vendor trust-boundary flaw in six AI coding assistants where a benign-looking repo file that is actually a symlink to a sensitive path makes the 'approve this edit' dialog display the innocent in-workspace path while the write lands outside the workspace — combining CWE-61 symlink following with CWE-451 UI misrepresentation to reduce human approval to a rubber stamp.

+ 19 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 ↗