Not If, But How: Responding to Security Incidents in the Age of AI Attackers

Attackers now operate at machine speed, using AI agents to scan, plan, and execute intrusions that improve every month. More companies will…

By Vane November 19, 2026 4 min read

Attackers now operate at machine speed, using AI agents to scan, plan, and execute intrusions that improve every month. More companies will face incidents in this environment. The difference lies in how they respond. Modern playbooks require four pillars: detect and contain automatically, communicate fast and securely, eradicate thoroughly, and shrink the blast radius. This analysis covers six months of incidents, using Fireworks AI as a model for a mature response.

TL;DR

  • The trend: AI-powered attackers drive more frequent attacks at global scale.
  • The evidence: Several AI platforms disclosed security incidents between May and November 2026.
  • Pillar 1: Detect and contain automatically. Human-speed shutdowns are too slow.
  • Pillar 2: Communicate fast and securely, over out-of-band channels.
  • Pillar 3: Eradicate thoroughly, with outside forensic experts.
  • Pillar 4: Keep shrinking the blast radius. Data that is never stored cannot be stolen.
  • Case studies: Fireworks AI and Klue show these pillars in practice.

Why are attacks becoming more frequent?

AI has changed the economics of attacking. Tasks that took skilled people days can now be delegated to agents.

In November, Google Threat Intelligence Group and Mandiant said AI misuse had reached a “critical inflection point”. They report that attackers use AI to shorten timelines and run multi-stage intrusions at machine speed. CrowdStrike reported that 1 group used AI agents against more than 200 organizations in 11 days. Palo Alto Networks’ Unit 42 found attacks moving about 4 times faster than a year earlier.

The shift started earlier. In 2025, Anthropic disrupted a campaign where AI did 80 to 90% of tactical work with little human input.

The tools keep improving, so the pace will keep rising. AI infrastructure is an especially attractive target, because AI access itself has value. The last 6 months show what that looks like.

What was disclosed in the last 6 months?

Incidents appeared across every layer of the AI stack. Together they show how broad the activity has become.

May: package registries. On May 10 and 11, the “Mini Shai-Hulud” campaign altered about 170 npm packages and some PyPI libraries. Affected projects included AI SDKs from Mistral AI and Guardrails AI. The NHS cyber alert lists the specific versions to avoid.

June: SaaS integrations. Klue, a market intelligence platform, disclosed misuse of OAuth tokens it held for customers. See case study 2.

August: self-hosted AI gateways. Microsoft described intrusions into exposed, unpatched LiteLLM, RAGFlow and Kestra deployments. Fixed versions exist for all 3 tools. CISA had listed the LiteLLM flaw as known exploited on June 8.

September: evaluation environments. Anthropic’s September threat report described attempts to obtain AI keys through software vendors. The Cloud Security Alliance summarized it. In 1 case, instructions were injected into a vendor’s automated evaluation sandbox.

October and early November: developer platforms. At least 9 AI developer and hosting platforms disclosed incidents involving stored customer secrets in October. Wiz’s tracker later listed further disclosures, for 16 platforms in total. A tampered LiteLLM release, version 1.107.0, was also identified, and users were told to roll back.

November: shared web vendors. On November 16, an attacker abused a flaw in Optimizely’s account signup flow to inject code into customer projects, reaching 178 organizations’ websites, according to Report URI, including HSBC, Salesforce, the BBC and Ledger. The code swapped crypto wallet addresses and skimmed payment forms; Optimizely removed the payload and fixed the flaw. Hudson Rock traced similar code through three other web services, beginning November 13. It is the same concentration pattern, one layer below the AI stack.

Date (2026)PlatformWhat was affectedEntry point, as reported
May 10 to 11npm and PyPI packages, incl. Mistral AI and Guardrails AI SDKsDeveloper and CI credentials on installing hostsPoisoned package releases
June 11 to 12KlueCustomer Salesforce and Gong dataLegacy credential, then stored OAuth tokens
AugustLiteLLM, RAGFlow, Kestra deploymentsModel provider keys, backend accessExposed, unpatched gateways
October 6Fireworks AIEnvironment variables in evaluation jobs, limited accountsMisused internal credentials
October 14 to 15Zeabur3,218,965 environment variable records, 321,810 accountsLong-lived admin tokens, exposed admin interface
October 15Lightning AICredentials; Studio taken offlineCredential access
October 16 to 17OpenCodeOpenAI, Anthropic and Google keys of about 1.4% of Console usersLegacy system
October 20 to 21RailwayEncrypted environment variables, some decryptedPrivilege escalation in build infrastructure
October 21LiteLLM 1.107.0Cloud credentials and LLM keys on installing hostsRelease pipeline compromise
October 23WarpAgent decision logs and telemetry, about 1% of usersThird-party vendor dependency
October 23 to 24Fireworks AIBilling data; for some customers, datasets and incomplete model weightsIncident at a third-party cloud provider
October 29CursorAltered extension copy in its marketplace cache, up to 5,000 usersCredential from exposed internal data
October 30NorthflankCustomers told to assume environment variables were decryptedNot disclosed
November 8NEAR AIInference server; 2 API keys exposed in logsRemote code execution flaw in SGLang

Selected incidents: Dates follow the linked sources, which sometimes differ by a day. Several October entries rely on compilations by Wiz and Helix rather than primary vendor disclosures.

What do these incidents have in common?

There was no single vulnerability. According to the Cloud Security Alliance, entry points varied. The common target was stored environment variables, often holding AI provider API keys.

AI keys carry real value, which explains the interest. CSA, citing Anthropic, notes that a key can be resold, used for compute or used as cover. Wiz estimated that misuse of 2 keys from these incidents exceeded $100,000 at list price. That is why spending caps matter.

Concentration is the other shared factor. A platform that stores secrets for many customers naturally draws attention. CSA describes this as the platform-chain pattern.

Scroll to Top