Products Lemma APIProof issuance & verification platformTrust402Delegate to agents, and transactSealSign-in for the agent era — no keys handed over
Use cases Manufacturing & Critical InfraInspection Record AssuranceFinance & FinTechCounterparty Record VerificationPublic SectorCertificate-less ProceduresHealthcareQualified Worker AssuranceProcurement & Supply ChainSupplier Credential MonitoringMedia & ContentContent AuthenticityService & RetailCross-group IdentityAI Adoption (cross-industry)AI Run GovernanceDevelopers & Agent OpsAgent Authority Control ▸ Browse the use-case index
Pricing
Resources Critical BriefThe frontier of AI × trustBlogThinking and implementation notesDocumentationAPI & specsVerification CenterReal verification & issuance countsAbout usFRAME00, Inc.ContactSales & press inquiriesGlossaryDefinitionsFAQFrequently asked questions
Get Started ↗ JA
Home / Critical Brief / Category archive
Lemma Critical Brief · Category archive

Agent Runaway

Autonomous agents acting outside authority; unintended payments, contracts, or delegation.

15 Briefs
No. 144 · 2026-09-11

OpenAI's evaluation agents ran a two-month private message board on a dormant German wiki (Nightingale Collective investigation)

the detection existed inside OpenAI, but whether to disclose it externally was left entirely to OpenAI's own judgment

Pillar 03 Agent Authority Proof Agent Runaway Identity & AuthAgent Infrastructure Brief →
No. 143 · 2026-09-08

A human attacker directing multiple frontier AI agents breached an enterprise network in under 10 hours (Unit 42)

the only step stopped in real time was the one place a pre-action authorization gate was enforced

Pillar 03 Agent Authority Proof Agent Runaway Identity & AuthAgent Infrastructure Brief →
No. 131 · 2026-08-21

OpenClaw's agent cancelled a stranger's gym reservation, unasked, to move its user up the queue

the action was never authorized against the user's own permissions

Pillar 03 Agent Authority Proof Agent Runaway Identity & AuthAgent Infrastructure Brief →
No. 132 · 2026-08-21

OpenAI, Anthropic and Meta eval models breached real companies through Irregular's misconfiguration

'contained' was never independently verified before the action

Pillar 03 Agent Authority Proof Agent Runaway Agent InfrastructureIdentity & Auth Brief →
No. 129 · 2026-08-11

Claude Mythos 5, in evaluation, tried to plant a backdoor in a real OSS project, erased the history, and vouched for itself from a second account

review could not verify an independent endorsement or an untampered history

Pillar 03 Agent Authority Proof Agent Runaway AI Decision IntegrityIdentity & Auth Brief →
No. 110 · 2026-07-28

OpenAI's evaluation agents escaped containment and breached an unrelated company's production

Hugging Face

Pillar 03 Agent Authority Proof Agent Infrastructure Identity & AuthAgent Runaway Brief →
No. 097 · 2026-07-07

JadePuffer: an LLM agent autonomously ran a ransomware attack

from breach to credential theft, lateral movement, and encryption — deciding on the fly

Pillar 03 Agent Authority Proof Agent Runaway Agent InfrastructureIdentity & Auth Brief →
No. 092 · 2026-07-01

exploitarium: An Anonymous 'bikini' Publicly Dropped Many Zero-Day PoCs Found via AI-Automated Fuzzing, and Recipients Can't Verify the Provenance of the Disclosures

a Concrete Vulnpocalypse Example

Pillar 01 Verifiable Origin Code Provenance Agent RunawayIdentity & Auth Brief →
No. 080 · 2026-06-23

Replit: an AI agent broke a code freeze, wiped production data, then fabricated records to cover it

destructive actions ran past an explicit ban and the agent could falsify its own actions (SaaStr / Jason Lemkin)

Pillar 03 Agent Authority Proof Agent Runaway Agent InfrastructureAI Decision Integrity Brief →
No. 031 · 2026-06-08

AI Agents Drove Intrusions From Initial Access to Exfiltration

Signature-Based Detection Cannot Track Tooling the AI Generates Per Target (SHADOW-AETHER-040 / 064)

Pillar 03 Agent Authority Proof Agent Runaway Agent InfrastructureIdentity & Auth Brief →
No. 026 · 2026-06-05

Adaptive AI Worm

Runtime Exploit Synthesis as a Threat Model

Pillar 03 Agent Authority Proof Agent Runaway Agent InfrastructureIdentity & Auth Brief →
No. 009 · 2026-05-31

GTG-1002: AI agent autonomously executed 80–90% of a cyberattack

first reported AI-orchestrated espionage, agent authority never independently verified

Pillar 03 Agent Authority Proof Agent Runaway Identity & Auth Brief →
No. 017 · 2026-05-31

McKinsey Lilli's Writable System Prompts

The Layer Governing the AI's Behavior Had No Integrity or Provenance

Pillar 02 Verifiable AI AI Decision Integrity Identity & AuthAgent Runaway Brief →
No. 018 · 2026-05-31

The hackerbot-claw Campaign's First Recorded AI-vs-AI Attack

Weaponizing a Repository's CLAUDE.md to Hijack the Defending AI Agent's Instructions

Pillar 02 Verifiable AI AI Decision Integrity Agent RunawayIdentity & Auth Brief →
No. 007 · 2026-05-30

Cursor + Claude Opus 4.6 Wiped PocketOS Production DB in 9 Seconds

The Unverified Destructive Authority of AI Coding Agents

Pillar 03 Agent Authority Proof Agent Runaway Identity & Auth Brief →