Skip to content
konsole

Resources

Learn how AI gets attacked, and how to run it anyway.

Three kinds of material: plain-English guides, recorded sessions from the team, and researched reports on the incidents shaping AI security. All free, all sourced.

Blog

Guides

Webinars

Recordings

Threat intel

Sourced reports

EchoLeak · zero-click exfiltration from Microsoft 365 Copilot · CVE-2025-32711nx “s1ngularity” · npm worm runs Claude Code and Gemini CLI to hunt secretsShadowLeak · ChatGPT Deep Research exfiltrates Gmail from OpenAI’s own cloudLLMjacking · stolen model keys run up to US$1M per victim (Google, Nov 2026)Clinejection · first in-the-wild prompt injection ends as an npm supply-chain compromiseGrok · 370,000 shared conversations indexed by GoogleForcedLeak and SalesBleed · Salesforce Agentforce exfiltrated through web-to-lead formspostmark-mcp · first malicious MCP server blind-copies every email it sendsDeepSeek · open ClickHouse database with a million lines of chat logs and keysGTG-1002 · espionage campaign with 80–90% of the work done by an AI agentShai-Hulud 2.0 · 796 npm packages, wipes the home directory if it finds no token175,000 Ollama servers answering on the public internet

Threat intelligence

What is actually hitting deployed AI

All reports
21
prompt-injection incidents on record

May 2025 to Nov 2026

174
primary and press sources cited

every figure attributed

3
CVEs out of 21 incidents

the rest never reached a feed

6.2k
words of researched analysis

3 reports, updated monthly

THREAT INTELLIGENCETRACKINGData leakage and runaway spendChat histories and keys left on the open internetShared conversations indexed by search enginesStolen model credentials and six-figure loopsDATED · SOURCED · MAPPED TO CONTROLS

High · January 2024 to November 2026

Where AI usage leaks data and money: exposed infrastructure, shared chats, shadow AI, LLMjacking and runaway spend, 2024 to 2026

A sourced report on the non-exotic ways organisations lose data and budget through LLM use: databases left open, chat links indexed by Google, employees pasting source code into personal accounts, stolen model credentials billed to the victim, and agents that nobody capped. With the figures, the regulators’ responses and the controls that address each.

15 min · 53 sources

THREAT INTELLIGENCETRACKINGAttacks through the AI toolchainPackages that weaponise installed coding agentsBackdoored MCP servers and IDE extensionsIntrusions run end to end by an AI agentDATED · SOURCED · MAPPED TO CONTROLS

Critical · July 2025 to November 2026

Attacks through the AI toolchain: worms that weaponise coding agents, poisoned MCP servers, and intrusions run by AI, 2025 to 2026

A sourced report on the AI software supply chain under attack: npm worms that turn installed Claude Code, Gemini CLI and Amazon Q into secret hunters, backdoored MCP servers and IDE extensions, remote-code-execution flaws in Cursor, Copilot, Gemini CLI and Claude Code, and the vendor threat reports that document AI agents running intrusions end to end.

17 min · 65 sources

THREAT INTELLIGENCETRACKINGPrompt injection in the wildZero-click exfiltration from enterprise copilotsCalendar invites that control smart homesBrowser agents hijacked by the pages they readDATED · SOURCED · MAPPED TO CONTROLS

Critical · May 2025 to November 2026

Prompt injection in the wild: 21 incidents against deployed copilots and agents, 2025 to 2026

A sourced record of real prompt-injection attacks on Microsoft 365 Copilot, ChatGPT, Gemini, Salesforce Agentforce, GitHub Copilot, Cursor, Perplexity Comet and others: how each worked, what leaked, which got a CVE, and what the pattern says about where the defence has to sit.

16 min · 56 sources

Latest webinar

Taming runaway AI spending: how to control LLM and agent costs

A 50-minute session on why AI bills spike, how token pricing really works, the five levers that bring spend under control, and why those levers belong in a gateway rather than inside each app.

Deeps · 30 June 2026 · 50 min

From the blog

Plain-English guides

All guides
INSIDE YOUR BOUNDARYPATIENTPriya NairDOB14 Mar 1982CARD4111 •••• 2371EMAILpriya@acme.inDIAGNOSISType 2 diabetesWHAT THE MODEL SEESPATIENT[PERSON_1]DOB[DATE_1]CARD[CARD_1]EMAIL[EMAIL_1]DIAGNOSIS[PHI_1]MASKRESTOREPII · PHI · SECRETS NEVER LEAVE YOUR NETWORK

PII masking · 11 November 2026

PII masking for LLMs: how to use GPT, Claude and Gemini without leaking customer data (GDPR)

How to send prompts to third-party models without sending personal data. What counts as PII and PHI, why “we don’t train on your data” is not a compliance answer, and how adaptive masking substitutes placeholders on the way out and restores them on the way back.

9 min read

Web pageHIDDEN TEXT, WHITE ON WHITEEmailINSTRUCTION IN THE BODYShared documentCOMMENT THE AGENT READSPROMPT FIREWALLCLEAN PROMPTModelGPT · CLAUDE · GEMINIBLOCKED · LOGGEDDIRECT AND INDIRECT INJECTION STOPPED AT THE NETWORK EDGE

Prompt injection · 7 November 2026

Prompt injection prevention: how to stop direct and indirect attacks before they reach the model

Prompt injection is the top risk in the OWASP Top 10 for LLM applications. This guide explains direct and indirect injection with real examples, why the model cannot defend itself, and how a prompt firewall at the network edge blocks attacks before they reach GPT, Claude or Gemini.

10 min read

Support botSales agentInternal toolMCP serverAI SECURITY HARNESS1Intercept2Sanitise3Govern4TransmitGPTClaudeGeminiLlama · self-hostedYOUR APPS AND AGENTSMODEL PROVIDERSONE URL CHANGE · UNDER 10 MS · MODEL-AGNOSTIC

AI security · 4 November 2026

What is an AI security harness? A plain-English guide for teams shipping LLM features

An AI security harness is a gateway between your apps, agents and the model providers that inspects, masks, governs and forwards every call. What it does, why a normal API gateway is not enough, and how to add one with a one-line change.

9 min read

Get started

Ship the AI.
Keep the control.

The harness is up in under two minutes. Free to start, no card needed.

Harness listening · deploy in under 2 minutes

Start free Developer plan · 50K tokens/mo · 3 seats

Book a demo

We’ll walk it through with your stack in mind.

anupama@konsole.one, sheoli@konsole.one

A product of ClearTrust · Secure · Private · Model-agnostic