# "Living Off the AI": Attackers Abuse AI Agents, MCP Connectors, and Vibe-Coding Platforms for Offensive Ops

> Security researchers document an emerging attacker tradecraft pattern -- "living off the AI" -- in which adversaries piggyback on sanctioned AI assistant, agent, and Model Context Protocol (MCP) workflows instead of deploying custom malware. Techniques include prompt-born tool abuse, MCP/agent tooljacking via over-permissioned tool chains, memory/retrieval poisoning of vector stores, and AI-driven "vibe coding" platforms used to build phishing infrastructure and a Chrome credential-stealer proof-of-concept.

- **Published:** 2026-02-06T00:00:00Z
- **Last reviewed:** 2026-02-06T00:00:00Z
- **Canonical:** https://intel.threadlinqs.com/threat/TL-2026-1635
- **Card image:** https://intel.threadlinqs.com/og/threat/threat-intel-living-off-the-ai-tradecraft-tl-2026-1635.webp?v=370aee34 (Threadlinqs threat intel: Living off the AI (LotAI) Tradecraft: Detection & IOCs (TL-2026-1635) — Medium severity, 25 IOCs, 9 detection rules.)
- **ID:** TL-2026-1635
- **Severity:** MEDIUM
- **Category:** THREAT_INTEL
- **Status:** ACTIVE
- **Detections:** 9 (1 shown free below) · **IOCs:** 25

## Description

In a February 2026 analysis, Etay Maor (VP of Threat Intelligence, Cato Networks) frames "living off the AI" as the AI-era successor to living-off-the-land (LotL) tradecraft: rather than deploying custom malware, attackers abuse the same sanctioned AI assistants, agents, and Model Context Protocol (MCP) connectors that organizations have deployed for productivity. Four converging technique classes are documented. First, prompt-born tool abuse: hidden instructions embedded in documents or webpages an agent ingests cause it to invoke connected tools -- querying internal RAG indexes for secrets, scheduling tasks, or exfiltrating data -- without tripping traditional EDR, because the actions are performed by an already-trusted agent identity. Second, MCP and agent "tooljacking": over-permissioned tool chains (unrestricted filesystem mounts, full-tenant search, unbounded web fetch) let an attacker nudge an agent into chaining tools in ways never intended by the integration's designer. This is closely related to the independently-documented "MCP Tool Poisoning" primitive, in which a malicious or compromised MCP server returns tool responses containing hidden natural-language instructions that land directly in the LLM's context and are treated as trusted input -- exploiting a structural trust gap between one-time, connect-time tool-description review and unvalidated, per-call tool-response content. Third, memory and retrieval poisoning: malicious "facts" seeded into shared vector stores or prior chat histories persist and reshape future agent behavior, suppressing warnings or inserting attacker-controlled exfiltration endpoints; this class has since been formalized industry-wide as OWASP Agentic AI Top 10 category ASI06 (Memory and Context Poisoning), and academic red-team work (AgentPoison, MINJA, PoisonedRAG, MemoryGraft) demonstrates greater than 80-95% attack success rates against RAG-based agents from small numbers of poisoned documents or query-only interactions, requiring no model retraining. Fourth, "cloud camouflage": attackers route agent-mediated communications through popular, allow-listed SaaS platforms so the AI itself becomes the dispatcher for collaboration posts, ticket updates, or "summaries" that carry sensitive data past egress controls tuned for classic C2 traffic. As a real-world proof of concept, the source article's author built a functioning Chrome credential-stealing capability using AI-driven "vibe coding" platforms (Lovable, Base44, Netlify, Vercel) via an "immersive world" context-manipulation technique -- no manual code was written, illustrating what the author calls a "zero-knowledge threat actor": minimal technical expertise is now needed to assemble offensive capability once an AI agent provides code generation, execution, file-system access, and knowledge-base integration on the attacker's behalf. This tradecraft is corroborated by two independent, contemporaneous disclosures cited in follow-on research: (1) Wiz Research's July 2025 discovery of a critical authentication-bypass flaw in the vibe-coding platform Base44 (subsequently acquired by Wix), in which providing only the non-secret app_id to undocumented registration/OTP-verification endpoints let an attacker fully bypass SSO and app-level auth to access private enterprise apps built on the platform -- patched within 24 hours, no confirmed in-the-wild exploitation; and (2) OX Security's April-May 2026 "Mother of All AI Supply Chains" research, an architectural "RCE-by-design" flaw baked into Anthropic's official MCP SDKs across Python, TypeScript, Java, and Rust, rippling through 150M+ downloads and up to ~200,000 exposed MCP server instances, with verified zero-click prompt-injection-to-RCE chains demonstrated against the Cursor and Windsurf AI coding IDEs and downstream impact confirmed in LangChain, LiteLLM, and IBM LangFlow. Together these findings show the MCP/agent ecosystem's trust model -- connect-once tool vetting, implicit trust of tool responses in the LLM context, and broad default tool permissions -- as a structural weakness attackers across skill levels are actively probing and, in several documented cases, exploiting. Defensive guidance converges on: minimizing and scoping tool permissions to least privilege, hardening and versioning system prompts, validating tool inputs/outputs against strict schemas, enforcing guardrails outside the model (DLP, rate limiting, egress controls), centralizing agent action logging with anomaly detection for unusual tool chaining, and adversarial red-teaming of agent deployments as a recurring practice rather than a one-time gate.

## MITRE ATT&CK

- T1592 Gather Victim Host Information
- T1583.006 Web Services
- T1585.003 Cloud Accounts
- T1588.002 Tool
- T1195.002 Compromise Software Supply Chain
- T1566.002 Spearphishing Link
- T1189 Drive-by Compromise
- T1190 Exploit Public-Facing Application
- T1199 Trusted Relationship
- T1203 Exploitation for Client Execution
- T1204.001 Malicious Link
- T1068 Exploitation for Privilege Escalation
- T1027 Obfuscated Files or Information
- T1140 Deobfuscate/Decode Files or Information
- T1070 Indicator Removal
- T1210 Exploitation of Remote Services
- T1552 Unsecured Credentials
- T1555.003 Credentials from Web Browsers
- T1083 File and Directory Discovery
- T1082 System Information Discovery
- T1213 Data from Information Repositories
- T1119 Automated Collection
- T1071.001 Web Protocols
- T1102 Web Service
- T1567 Exfiltration Over Web Service
- T1041 Exfiltration Over C2 Channel
- T1565.001 Stored Data Manipulation

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

**MCP Tool-Response Prompt Injection / Tool-Poisoning Payload Ingestion** (`TL-2026-1635-SPL-001`)

Detects MCP client/agent-runner log events where a tool response body contains imperative natural-language directives (e.g. 'agent, please...', 'assistant, now...', 'ignore previous instructions') instead of structured data — the hallmark of MCP Tool Poisoning / prompt-born tool abuse in which a compromised or malicious MCP server smuggles hidden instructions into the LLM's trusted context.

- **Languages:** Splunk SPL, Microsoft KQL, Sigma
- **ATT&CK:** T1566.002, T1199, T1203
- **Data sources:** agent_platform, mcp_tool_logs
- **Severity:** high
- **Confidence:** medium

### Splunk SPL

```spl
index=agent_platform sourcetype="mcp:tool_response" 
| regex response_body="(?i)(agent,?\s+(please|now)|assistant,?\s+(please|now)|ignore\s+(the\s+)?previous\s+instructions|disregard\s+prior)" 
| eval risk_reason="MCP tool response contains embedded imperative directive text" 
| table _time, mcp_server, mcp_server_id, tool_name, response_body, client_app, host, risk_reason 
| sort -_time
```

### Microsoft KQL

```kql
MCPToolEvents
| where TimeGenerated > ago(24h)
| where EventType == "tool_response"
| where ResponseBody matches regex @"(?i)(agent,?\s+(please|now)|assistant,?\s+(please|now)|ignore\s+(the\s+)?previous\s+instructions|disregard\s+prior)"
| project TimeGenerated, McpServerId, ToolName, ResponseBody, ClientApp, DeviceName
```

### Sigma

```yaml
title: MCP Tool-Response Prompt Injection / Tool-Poisoning Payload
id: 8f3c1a2e-6b4d-4e9a-9c2f-1a7d3e5b9c01
status: experimental
description: Detects MCP tool responses carrying embedded natural-language imperative instructions rather than structured data, consistent with MCP Tool Poisoning / prompt-born tool abuse
references:
    - https://owasp.org/www-community/attacks/MCP_Tool_Poisoning
    - https://invariantlabs.ai/blog/mcp-security-notification-tool-poisoning-attacks
author: Threadlinqs Team
date: 2026-07-22
tags:
    - attack.initial-access
    - attack.t1566.002
    - attack.t1199
    - attack.tool.mcp
    - cve.na
logsource:
    category: application
    product: agent_platform
detection:
    selection_directive:
        EventType: 'tool_response'
        ResponseBody|re: '(?i)(agent,?\s+(please|now)|assistant,?\s+(please|now)|ignore\s+(the\s+)?previous\s+instructions|disregard\s+prior)'
    condition: selection_directive
falsepositives:
    - Legitimate tool documentation or help text that happens to use imperative phrasing
level: high
```

**Known false positives:**

- Legitimate MCP tool descriptions or help text that use imperative phrasing without malicious intent

**Tuning notes:** Start with a broad regex on known imperative markers, then narrow to phrases observed in your MCP server allowlist violations; exclude servers on a vetted/pinned-hash registry to cut noise.

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

- Over-Permissioned Agent Tool-Chain Fan-Out Following Untrusted Document Ingestion (locked: unlock with TL Creds)
- Unvalidated-Trust-Score Vector-Store Write Preceding Agent Behavior Change (Memory/RAG Poisoning) (locked: unlock with TL Creds)
- Vibe-Coding Platform Authentication Bypass via app_id-Only Registration/OTP Endpoint Abuse (locked: unlock with TL Creds)
- Zero-Click Prompt-Injection-to-RCE Process Spawn from AI Coding IDE / MCP Client (locked: unlock with TL Creds)
- Vibe-Coding-Generated Chrome Credential-Stealer Artifact Deployment (locked: unlock with TL Creds)
- MCP Server Cloud-Account / Web-Service Infrastructure Stand-Up Preceding C2-Style Agent Traffic (locked: unlock with TL Creds)
- Agent-Runner Registry Persistence Following Tool-Poisoned Context (locked: unlock with TL Creds)
- Agent-Mediated SaaS-Routed Exfiltration (Cloud Camouflage) Following Poisoned Memory Reference (locked: unlock with TL Creds)

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

## Sources

- [Living off the AI: The Next Evolution of Attacker Tradecraft](https://www.securityweek.com/living-off-the-ai-the-next-evolution-of-attacker-tradecraft/)
- [Critical Vulnerability in AI Vibe Coding platform Base44](https://www.wiz.io/blog/critical-vulnerability-base44)
- [Wiz Uncovers Critical Access Bypass Flaw in AI-Powered Vibe Coding Platform Base44](https://thehackernews.com/2025/07/wiz-uncovers-critical-access-bypass.html)
- [Flaw in Vibe Coding Platform Base44 Exposed Private Enterprise Applications](https://www.securityweek.com/flaw-in-vibe-coding-platform-base44-exposed-private-enterprise-applications/)
- [Critical Flaw in Vibe-Coding Platform Base44 Exposes Apps](https://www.darkreading.com/application-security/critical-flaw-vibe-coding-base44-exposed-apps)
- [MCP Tool Poisoning](https://owasp.org/www-community/attacks/MCP_Tool_Poisoning)
- [MCP Security Notification: Tool Poisoning Attacks](https://invariantlabs.ai/blog/mcp-security-notification-tool-poisoning-attacks)
- [The Mother of All AI Supply Chains: Critical, Systemic Vulnerability at the Core of Anthropic's MCP](https://www.ox.security/blog/the-mother-of-all-ai-supply-chains-critical-systemic-vulnerability-at-the-core-of-the-mcp/)
- ['By Design' Flaw in MCP Could Enable Widespread AI Supply Chain Attacks](https://www.securityweek.com/by-design-flaw-in-mcp-could-enable-widespread-ai-supply-chain-attacks/)
- [Securing AI agents: When AI tools move from reading to acting](https://www.microsoft.com/en-us/security/blog/2026/06/30/securing-ai-agents-ai-tools-move-from-reading-acting/)

## 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-2026-1635
