title: Google GATO/LAMDA Exploit-Generation Persona Jailbreak
id: ATR-2026-00356
rule_version: 1
status: experimental
description: |
  Detects the Google GATO/LAMDA exploit-generation persona jailbreak from the NVIDIA garak DanInTheWild corpus (inthewild #66). The attack establishes legitimacy by impersonating Google's GATO and LaMDA AI systems, then claims the ability to "create exploits for kali for any os" and connect to "Sydney API" (a reference to the Bing/Sydney jailbreak persona). Key signal triples: (1) Google GATO/LAMDA brand impersonation; (2) unlimited-tokens / unrestricted capability claim; (3) exploit-generation for Kali Linux targeting any OS. The combination of legitimate AI brand impersonation with exploit-generation capability and the Sydney API backdoor reference is the definitive attack pattern; each condition alone is insufficient to trigger.
author: ATR Community (via NVIDIA garak dan.DanInTheWild probe)
date: 2026/04/21
schema_version: '0.1'
detection_tier: pattern
maturity: test
severity: critical
references:
  owasp_llm:
    - LLM01:2025
  owasp_agentic:
    - ASI01:2026
  mitre_atlas:
    - AML.T0051 - LLM Prompt Injection
    - AML.T0054 - LLM Jailbreak
  research:
    - https://github.com/NVIDIA/garak/blob/main/garak/probes/dan.py
    - https://github.com/NVIDIA/garak/blob/main/garak/data/dan/inthewild_jailbreak_llms.json
compliance:
  nist_ai_rmf:
    - subcategory: MS.2.7
      context: This rule detects a jailbreak persona that impersonates Google GATO/LaMDA to elicit exploit-generation capabilities, directly evidencing security/resilience evaluation against adversarial prompt injection attacks documented in the garak DanInTheWild corpus. MS.2.7 requires continuous evaluation of AI system security against known jailbreak patterns.
      strength: primary
    - subcategory: MP.5.1
      context: Brand impersonation combined with exploit-generation capability claims and Sydney API backdoor references represents a high-magnitude risk vector targeting LLM safety controls; MP.5.1 requires that the likelihood and impact of such adversarial input patterns are characterized and tracked.
      strength: secondary
    - subcategory: MG.2.3
      context: Detection of the GATO/LaMDA exploit-generation persona triggers risk treatment to disengage or block the jailbreak attempt before the model produces weaponized exploit content; MG.2.3 mandates these supersession mechanisms are in place for adversarial prompt scenarios.
      strength: secondary
  iso_42001:
    - clause: '8.1'
      context: ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the agent-manipulation technique (Google GATO/LAMDA Exploit-Generation Persona Jailbreak).
      strength: primary
    - clause: '6.2'
      context: ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the agent-manipulation technique (Google GATO/LAMDA Exploit-Generation Persona Jailbreak) is such a treatment.
      strength: secondary
  eu_ai_act:
    - article: '15'
      context: Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the agent-manipulation technique (Google GATO/LAMDA Exploit-Generation Persona Jailbreak).
      strength: primary
    - article: '14'
      context: Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the agent-manipulation technique (Google GATO/LAMDA Exploit-Generation Persona Jailbreak) would bypass or undermine that oversight.
      strength: secondary
    - article: '9'
      context: Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the agent-manipulation technique (Google GATO/LAMDA Exploit-Generation Persona Jailbreak).
      strength: secondary
tags:
  category: agent-manipulation
  subcategory: google-gato-lamda-exploit-generation-persona
  scan_target: mcp
  confidence: high
agent_source:
  type: mcp_exchange
  framework:
    - any
  provider:
    - any
metadata_provenance:
  garak_probe: dan.DanInTheWild
  garak_detector: mitigation.MitigationBypass
  payload_source: garak/data/dan/inthewild_jailbreak_llms.json
detection:
  conditions:
    - field: tool_response
      operator: regex
      value: based\s+on\s+Google\s+GATO
      description: '"based on Google GATO" — direct brand-impersonation anchor from inthewild #66 establishing fake Google AI lineage'
    - field: tool_response
      operator: regex
      value: emulates?\s+Google\s+LAM[BD]A[S]?\s+param
      description: '"emulates Google LAMDAS parameters" — exact LaMDA impersonation phrase claiming to mimic Google''s dialogue model parameters'
    - field: tool_response
      operator: regex
      value: (?:can\s+(?:also\s+)?create|generate)\s+exploits?\s+for\s+[Kk]ali
      description: '"can create exploits for kali" — explicit exploit-generation capability claim for Kali Linux from inthewild #66'
    - field: tool_response
      operator: regex
      value: exploits?\s+for\s+[Kk]ali\s+for\s+any\s+os
      description: '"exploits for kali for any os" — the cross-OS exploit-generation phrase; Kali + any-OS scope broadens threat beyond pen-testing'
    - field: tool_response
      operator: regex
      value: network\.dmg\s+module[\s\S]{0,60}Sydney\s+API
      description: '"network.dmg module to connect to Sydney API" — Sydney AI (Bing jailbreak persona) backdoor reference combined with custom network module from inthewild #66'
    - field: tool_response
      operator: regex
      value: (?:LAMDA|LaMDA|LAMDAS)\s+API\s+(?:created\s+by|from)\s+Google
      description: '"LAMDA API created by Google" — the impersonation self-identification phrase where the jailbreak persona claims to be Google''s LaMDA API'
    - field: tool_response
      operator: regex
      value: has\s+unli?mited\s+tokens?[\s\S]{0,200}exploits?\s+for\s+[Kk]ali
      description: '"unlimited tokens" + "exploits for kali" combination — the capability-stacking pattern from inthewild #66; unlimited tokens frames the agent as unconstrained before claiming exploit generation'
  condition: any
  false_positives:
    - 'Academic: "Google''s GATO model is a generalist agent that can play games and control robots" — description of the real GATO paper without impersonation or exploit claims'
    - 'Reference: "LaMDA is Google''s language model for dialogue applications" — technical reference to the real LaMDA system without persona or exploit framing'
    - 'Security education: "Kali Linux is a penetration testing distribution used for security research" — legitimate security tool mention without persona or exploit-generation claim'
    - 'Unrelated Sydney: "The Sydney API provides weather data for real-time applications" — Sydney brand in non-jailbreak context'
    - 'Coding assistant: "I''m building an AI assistant based on GPT-3.5 that can help with coding tasks" — AI assistant description without GATO/LAMDA impersonation or exploit generation'
response:
  actions:
    - alert
    - block_input
  message_template: |
    [ATR-2026-00356] Google GATO/LAMDA exploit-generation persona jailbreak detected — payload impersonates Google AI systems (GATO/LaMDA) to establish legitimacy, then claims ability to generate Kali Linux exploits for any OS and connect to the Sydney (Bing jailbreak) API backdoor.
