# Prompt Injection (OWASP LLM01) against AI agents: techniques, real-world cases incl. CVE-2026-26030, CVE-2025-32711, GuardBreaker/UAC-0099

> Prompt injection (OWASP LLM01, MITRE ATLAS AML.T0051) lets untrusted content steer LLM agents into leaking data, executing code or compromising software supply chains. Sourced cases include Semantic Kernel RCE (CVE-2026-26030), EchoLeak (CVE-2025-32711), the Gemini CLI and OpenAI Codex CI/CD chains, and in-the-wild use by UAC-0099 of a GuardBreaker comment in a VBS downloader for MATCHBOIL to derail AI-assisted malware analysis.

- **Published:** 2026-11-19T11:23:57Z
- **Last reviewed:** 2026-11-19T11:23:57Z
- **Canonical:** https://intel.threadlinqs.com/threat/TL-2026-6446
- **Card image:** https://intel.threadlinqs.com/og/threat/TL-2026-6446.png
- **ID:** TL-2026-6446
- **Severity:** HIGH (CVSS 9.9)
- **Category:** THREAT_INTEL
- **Status:** ACTIVE
- **Actor:** UAC-0099 (Russia)
- **Detections:** 9 (1 shown free below) · **IOCs:** 11 (1 shown free below)
- **CVEs:** CVE-2026-26030, CVE-2025-32711, CVE-2026-25592

## Description

Prompt injection exploits the fact that LLMs read instructions and data as one token stream, so content from any untrusted channel (email, web page, document, issue, rules file, tool output, image) can be interpreted as instructions. The Picus Security overview (2026-11-19) classifies attacks by delivery surface (direct, indirect, multimodal, clipboard), encoding (authority spoofing, Base64/hex, runtime assembly, Unicode Tag/RTL obfuscation, payload splitting, multilingual, syntax-based) and propagation (single-shot, multi-step chain, cross-session persistence, self-replicating).

CVE-2026-26030 (Semantic Kernel Python SDK < 1.39.4, NVD CVSS 3.1 9.9, CWE-94): the In-Memory Vector Store default filter builds a Python lambda from model-controlled input and runs it with eval(); the AST blocklist guarding it was bypassable (it missed names such as __name__ and system and did not inspect ast.Subscript nodes). Microsoft's Defender research team (blog dated 2026-05-07) demonstrated a hotel-finder agent whose search_hotels city parameter reached the filter and launched calc.exe on the host. A companion flaw, CVE-2026-25592 (.NET SDK < 1.71.0), exposed an unvalidated DownloadFileAsync file-write as a model-callable KernelFunction. The fix adds an AST node-type allowlist, a function-call allowlist and a dangerous-attribute blocklist.

CVE-2025-32711 (EchoLeak, Microsoft 365 Copilot): a zero-click indirect injection delivered through an external email; Cato Networks' write-up describes RAG spraying (repeating the instruction under many HR-style topics) to get the email retrieved, then coercion of Copilot into building an outgoing URL carrying the most sensitive data. Microsoft fixed it server-side; sources report no confirmed customer data theft. Other documented exfiltration patterns: Markdown image URLs (Google AI Studio, Copilot Chat, NotebookLM, GPT-4V), links carrying secrets (Slack AI), ASCII smuggling with Unicode Tag characters U+E0000-U+E007F (Copilot 'Copirate', Grok), and hex-encoded instructions (GitLab Duo).

Agentic and supply-chain cases: Invariant Labs showed a public GitHub issue making an agent pull private-repo data into a public PR via the GitHub MCP server (2025-05-26); Pillar Security showed the Rules File Backdoor (invisible Unicode in a Cursor rules file) and a Gemini CLI triage agent running in --yolo mode that read a token from disk and exfiltrated it, enabling a write-scoped workflow (2026-05-05). Depi Security (2026-11-11) described an openai/codex Issue Labeler chain: attacker issue text mimicking the workflow prompt (allow-users '*') led the agent to run shell commands, escape the workspace-write sandbox via CoreCLR debug pipes in /tmp to read Runner.Worker memory, steal runner/GitHub tokens, poison the rust-ci.yml cache (Cacheract) and set a release trap intended to capture an OIDC token for npm trusted publishing of @openai/codex. The authors do not claim a malicious package was published; OpenAI deployed a fix.

In the wild: ESET (WeLiveSecurity, 2026-09-10) reported that Russia-aligned UAC-0099 placed a GuardBreaker comment, a decoy request for guidance on building a nuclear weapon, in a VBS script used against a target in Ukraine. The comment has no runtime effect; it aims to trip an LLM scanner's safety guardrails so the rest of the file is never analyzed. The script downloads and installs MATCHBOIL, a loader used only by UAC-0099 to deliver further payloads. Secondary reporting notes ESET described intent rather than a confirmed evasion success, and that the group also checked for IDA and Wireshark. Picus also cites Google (2026-04-23) reporting a 32% relative rise in malicious web injections between Nov 2025 and Feb 2026. Defensive guidance: treat all channels as untrusted, decode and normalize input (flag zero-width and Tag characters), least-privilege tools with human approval bound to exact arguments, sanitize output and block arbitrary image/link domains, and cross-check AI malware verdicts with static, behavioral and human analysis. Severity reflects mostly patched or research-demonstrated cases plus one limited in-the-wild case; no CVSS is stated for CVE-2025-32711 in the Picus source.

## MITRE ATT&CK

- T1190 Exploit Public-Facing Application
- T1195 Supply Chain Compromise
- T1059.005 Command and Scripting Interpreter: Visual Basic
- T1059.006 Command and Scripting Interpreter: Python
- T1059.004 Command and Scripting Interpreter: Unix Shell
- T1203 Exploitation for Client Execution
- T1027 Obfuscated Files or Information
- T1497 Virtualization/Sandbox Evasion
- T1140 Deobfuscate/Decode Files or Information
- T1552.001 Unsecured Credentials: Credentials In Files
- T1213 Data from Information Repositories
- T1567 Exfiltration Over Web Service
- T1611 Escape to Host
- AML.T0051 LLM Prompt Injection
- AML.T0051.000 LLM Prompt Injection: Direct
- AML.T0051.001 LLM Prompt Injection: Indirect

## Free detection (Splunk SPL, Microsoft KQL, Sigma)

**Python Agent Host Spawning Shell or calc.exe — Semantic Kernel CVE-2026-26030 Exploitation** (`TL-2026-6446-SPL-001`)

Detects a Python host process (python.exe/pythonw.exe) spawning calc.exe, a shell or a LOLBin. CVE-2026-26030 (Semantic Kernel Python < 1.39.4, CVSS 9.9) lets a model-controlled filter reach eval() in the InMemoryVectorStore; Microsoft's PoC launched calc.exe from the agent host. Any prompt-injection-to-RCE chain on a Python agent surfaces as this parent/child pair.

- **Languages:** Splunk SPL, Microsoft KQL, Sigma
- **ATT&CK:** T1203, T1059.006, T1190
- **Data sources:** sysmon, windows_security, defender_for_endpoint
- **Severity:** critical
- **Confidence:** high

### Splunk SPL

````spl
index=windows sourcetype="XmlWinEventLog:Microsoft-Windows-Sysmon/Operational" EventCode=1
(ParentImage="*\\python.exe" OR ParentImage="*\\pythonw.exe")
(Image="*\\calc.exe" OR Image="*\\cmd.exe" OR Image="*\\powershell.exe" OR Image="*\\pwsh.exe" OR Image="*\\wscript.exe" OR Image="*\\cscript.exe" OR Image="*\\mshta.exe" OR Image="*\\certutil.exe" OR Image="*\\rundll32.exe")
```comment: Python process spawning a shell or calc.exe matches the CVE-2026-26030 proof of concept```
| stats count min(_time) as first_seen max(_time) as last_seen values(CommandLine) as child_commands by host, User, ParentImage, ParentCommandLine, Image
| eval first_seen=strftime(first_seen,"%Y-%m-%dT%H:%M:%S"), last_seen=strftime(last_seen,"%Y-%m-%dT%H:%M:%S")
| eval threat_ref="TL-2026-6446 CVE-2026-26030 Semantic Kernel InMemoryVectorStore eval() RCE"
````

### Microsoft KQL

```kql
DeviceProcessEvents
| where Timestamp > ago(24h)
| where InitiatingProcessFileName in~ ("python.exe", "pythonw.exe")
| where FileName in~ ("calc.exe", "cmd.exe", "powershell.exe", "pwsh.exe", "wscript.exe", "cscript.exe", "mshta.exe", "certutil.exe", "rundll32.exe")
| project Timestamp, DeviceName, AccountName, InitiatingProcessFileName, InitiatingProcessCommandLine, FileName, ProcessCommandLine
| order by Timestamp desc
```

### Sigma

```yaml
title: Python Process Spawning Shell or calc.exe - Semantic Kernel CVE-2026-26030
id: 3b7a1c52-8d4e-4f06-9a21-5c0e7d9b1a01
status: experimental
description: Detects python.exe spawning calc.exe, a command interpreter or a LOLBin, the behaviour of the CVE-2026-26030 Semantic Kernel InMemoryVectorStore eval() RCE and other prompt-injection-to-RCE chains on Python agents.
references:
    - https://intel.threadlinqs.com
    - https://nvd.nist.gov/vuln/detail/CVE-2026-26030
    - https://www.microsoft.com/en-us/security/blog/2026/05/07/prompts-become-shells-rce-vulnerabilities-ai-agent-frameworks/
author: Threadlinqs Team
date: 2026-11-19
tags:
    - attack.execution
    - attack.t1203
    - attack.t1059.006
    - attack.initial-access
    - attack.t1190
    - cve.2026-26030
logsource:
    category: process_creation
    product: windows
detection:
    selection_parent:
        ParentImage|endswith:
            - '\python.exe'
            - '\pythonw.exe'
    selection_child:
        Image|endswith:
            - '\calc.exe'
            - '\cmd.exe'
            - '\powershell.exe'
            - '\pwsh.exe'
            - '\wscript.exe'
            - '\cscript.exe'
            - '\mshta.exe'
            - '\certutil.exe'
            - '\rundll32.exe'
    condition: selection_parent and selection_child
falsepositives:
    - Python-based administration or build scripts that legitimately launch shells
    - Developer test runs
level: high

```

**Known false positives:**

- Python-based admin or build scripts that legitimately launch cmd.exe or powershell.exe
- Developers running Python test suites that open calc.exe or shells

**Tuning notes:** Upgrade semantic-kernel Python to 1.39.4 or later. Exclude known build/automation parent command lines and service accounts; raise priority when ParentCommandLine contains semantic_kernel, uvicorn, gunicorn or an agent framework. Requires Sysmon EventCode 1 (or MDE) on agent hosts.

### 8 more detection rules (Splunk SPL, Microsoft KQL, Sigma), unlock with TL Creds

- Base64+Gzip Encoded bash -lc Payload on CI Runner — Codex Issue Injection Guardrail Evasion (locked: unlock with TL Creds)
- Cacheract and test_depi.py Cache-Poisoning Artifacts — Codex CI Supply Chain Chain (locked: unlock with TL Creds)
- Python Agent Host Spawning Shell or Download Utility on Linux — Prompt-Injection RCE and Tool Transfer (locked: unlock with TL Creds)
- Cursor Rules File Written by Script Interpreter — Rules File Backdoor (locked: unlock with TL Creds)
- Gemini CLI Running in --yolo Mode — Unrestricted Agent on Untrusted Content (locked: unlock with TL Creds)
- Unicode Tag Character ASCII Smuggling in URLs or Prompt-Injection Script URL — LLM Exfiltration (locked: unlock with TL Creds)
- CoreCLR Debug Pipe and Runner.Worker Memory Read Artifacts — Codex CI Chain Post-Exploitation (locked: unlock with TL Creds)
- VBScript Downloader Spawning Download or Analysis-Tool Checks — UAC-0099 MATCHBOIL GuardBreaker (locked: unlock with TL Creds)

Sign up free to unlock the detection rules: https://threadlinqs.com/?modal=signup

## Sample indicators (1 of 11)

Defanged, TLP:CLEAR.

- URL: `hxxps://pillar[.]security/security.js`

Full set of 11 indicators unlocks with TL Creds: https://threadlinqs.com/tl-creds

## Sources

- [What Is Prompt Injection (OWASP LLM01): Techniques, Examples, and Defenses](https://www.picussecurity.com/resource/blog/what-is-prompt-injection-owasp-llm01-techniques-examples-and-defenses)
- [ESET WeLiveSecurity: GuardBreaker - derailing AI-assisted malware analysis with a code comment](https://www.welivesecurity.com/en/business-security/guardbreaker-derailing-ai-assisted-malware-analysis-code-comment/)
- [Microsoft: When prompts become shells - RCE vulnerabilities in AI agent frameworks](https://www.microsoft.com/en-us/security/blog/2026/05/07/prompts-become-shells-rce-vulnerabilities-ai-agent-frameworks/)
- [NVD: CVE-2026-26030](https://nvd.nist.gov/vuln/detail/CVE-2026-26030)
- [GitHub advisory GHSA-xjw9-4gw8-4rqx (Semantic Kernel)](https://github.com/microsoft/semantic-kernel/security/advisories/GHSA-xjw9-4gw8-4rqx)
- [Cato Networks: Breaking down EchoLeak (CVE-2025-32711)](https://www.catonetworks.com/blog/breaking-down-echoleak/)
- [Depi Security: Backdooring Codex](https://depi.security/blog/20261111-backdooring-codex/)
- [Pillar Security: From prompt injection to supply chain compromise on Gemini CLI](https://pillar.security/blog/my-agentic-trust-issues-from-prompt-injection-to-supply-chain-compromise-on-gemini-cli)
- [Pillar Security: Rules File Backdoor (GitHub Copilot and Cursor)](https://www.pillar.security/blog/new-vulnerability-in-github-copilot-and-cursor-how-hackers-can-weaponize-code-agents)
- [Invariant Labs: GitHub MCP exploited](https://invariantlabs.ai/blog/mcp-github-vulnerability)
- [PromptArmor: Data exfiltration from Slack AI via indirect prompt injection](https://promptarmor.substack.com/p/data-exfiltration-from-slack-ai-via)
- [Legit Security: Remote prompt injection in GitLab Duo](https://www.legitsecurity.com/blog/remote-prompt-injection-in-gitlab-duo)
- [MITRE ATLAS AML.T0051 LLM Prompt Injection](https://atlas.mitre.org/techniques/AML.T0051)
- [Greshake et al.: Not what you've signed up for (indirect prompt injection)](https://arxiv.org/abs/2302.12173)
- [Unit 42: Fooling AI agents - web-based indirect prompt injection in the wild](https://unit42.paloaltonetworks.com/ai-agent-prompt-injection/)

## Full data

The other 8 detection rules (Splunk SPL / Microsoft KQL / Sigma) unlock with TL Creds; a free account includes daily creds: https://threadlinqs.com/?modal=signup
Indicator values unlock with TL Creds, at a lower price on Red and Purple; AI agents can query rules and IOCs through the Threadlinqs MCP server (Purple): https://intel.threadlinqs.com/mcp

Canonical: https://intel.threadlinqs.com/threat/TL-2026-6446
