13 · Availability Abuse

Explore 9 source-supported AI security cases for 13 · Availability Abuse in Cisco AI Security & Safety Framework v2.0, with evidence, scope, and defensive analysis.

Risk category

An attacker disrupts access to an AI model, agent, or service through resource exhaustion, performance degradation, or an outage. Cisco also includes cost harvesting and repurposing: unauthorized resource use or deliberately expensive workloads can inflate the owner's bill or consume capacity for the attacker's benefit. Overloading human review is another listed route. The harm can therefore be loss of usable service, financial burden, or both, even if the system has not completely stopped.

Official framework source ↗ · Open interactive explorer ↗

Incident ·

GTIG / Mandiant: Multi-Cloud LLMJacking and "LLM Mixer" Monetization

Google Threat Intelligence Group and Mandiant reported LLMJacking across several 2026 investigations: actors used other organizations' credentials to run cloud language models at the victims' expense. Some incidents incurred more than US$100,000 in a day. A separate token-routing service handled over 500,000 calls in less than eight hours, passing nearly US$1 million in costs to one victim. The investigations show several routes into cloud or AI gateways and different ways to cash out. For LiteLLM operators, v1.83.14-stable includes the fix for the cited CVE but still lacks the key ownership-change check added in v1.84.0.

Why it relates: In documented cost-harvesting cases, the attackers used the victims’ model access while leaving the billing with the account owners.

Evaluate each observed pattern with its own supporting investigation. The reported key-regeneration behavior and the case-wide advisory identifier are distinct source facts.

AIA · Read the full case ↗ · SecureFlow · Read the full case ↗

Incident ·

Railway: Build Isolation Failure and a Separate OIDC Re-entry Exposed AI Credentials

Railway is an application deployment platform. Railway reports an October 20 partial build-host filesystem escape, misuse of a build credential against Temporal and theft of its internal monorepo. After that route was contained, an erroneous OIDC binding enabled a second entry to production credentials and variable decryption. At most 1.85% of workspaces could have had variables decrypted; this is an upper bound, not proof that every variable was stolen. Subsequent misuse of AI keys was observed.

Why it relates: Unauthorized reuse of stolen AI credentials consumed AI services and imposed financial cost on the credential owners.

AI relevance comes from exposed credentials and subsequent AI-service abuse. The original platform entry is not an LLM exploit.

AIA · Read the full case ↗ · SecureFlow · Read the full case ↗

Incident ·

ComfyUI Botnet: Custom-Node Execution, Malicious Installs and Reinfection

Censys investigated a campaign targeting internet-exposed ComfyUI, a node-based interface for image-generation workflows. The operator used executable custom nodes or reachable Manager installation APIs to run a payload that deployed miners, a proxy service and reinfection mechanisms. Recovered scanner code and logs support the campaign; exposed-server counts do not establish how many hosts were infected.

Why it relates: The recovered payload repurposes AI-hosting resources for mining and proxy operation, matching Cisco’s cost-harvesting/repurposing branch without requiring a complete outage.

Custom-node and dependency execution in an image-generation runtime. Agent/LLM categories state the shared mechanism without assuming those deployments.

AIA · Read the full case ↗ · SecureFlow · Read the full case ↗

Incident ·

Vertex AI Resource Theft: About NT$30,000 in an Hour and the Limits of Budget Alerts

Physician and developer Lin reported about NT$30,000 in unauthorized Vertex AI charges within an hour across his Google Cloud projects. His first-person account, republished by Business Next, links those calls to unfamiliar service accounts (machine identities) created roughly two weeks earlier; Google subsequently adjusted most charges. The case concerns cloud AI resource theft, while the initial compromise path and any attacker use of AI agents remain unverified.

Why it relates: Unauthorized paid model calls generated a reported NT$30,000 bill within an hour. Cisco OB-013 explicitly includes cost harvesting and unauthorized resource repurposing, so its financial-abuse branch fits without asserting model-service denial or knowing the generated content.

A source-reported Google Cloud AI resource-theft incident. Mappings cover paid model consumption, unauthorized cloud administration and inference access. The MAESTRO overlap is limited to infrastructure resource hijacking; it does not assert an agent runtime.

AIA · Read the full case ↗

Incident ·

LLM Jacking

Sysdig observed stolen cloud credentials used to probe hosted LLM access and logging, then support reverse-proxy access that could be resold. The entry exploit, possession of credentials, tool preparation and provider-side use are distinct steps. The flow preserves parallel preparation before service use. Potential daily costs are estimates; provider-native IAM and complete invocation telemetry constrain direct calls that bypass an application proxy.

Why it relates: The Sysdig Threat Research Team discovered that malicious actors utilized stolen credentials to gain access to cloud-hosted large language models (LLMs). The relevant category is Availability Abuse: An attacker disrupts access to an AI model, agent, or service through resource exhaustion, performance degradation, or an outage.

The Sysdig Threat Research Team discovered that malicious actors utilized stolen credentials to gain access to cloud-hosted large language models (LLMs). The actors covertly gathered information about which models were enabled on the cloud service and created a reverse proxy for LLMs that would allow them to provide model access to cybercriminals. The Sysdig researchers identified tools used by the unknown actors that could target a broad range of cloud services including AI21 Labs, Anthropic, AWS Bedrock, Azure, ElevenLabs, MakerSuite, Mistral, OpenAI, OpenRouter, and GCP Vertex AI. Their technical analysis represented in the procedure below looked at at Amazon CloudTrail logs from the Amazon Bedrock service. The Sysdig researchers estimated that the worst-case financial harm for the unauthorized use of a single Claude 2.x model could be up to $46,000 a day. Update as of April 2025: This attack is ongoing and evolving. This case study only covers the initial reporting from Sysdig.

SecureFlow · Read the full case ↗

Validated Research ·

Achieving Code Execution in MathGPT via Prompt Injection

The publicly available Streamlit application MathGPT (https://mathgpt.streamlit.app/) uses GPT-3, a large language model (LLM), to answer user-generated math questions. Recent studies and experiments have shown that LLMs such as GPT-3 show poor performance when it comes to performing exact math directly. However, they can produce more accurate answers when asked to generate executable code that solves the question at hand. In the MathGPT application, GPT-3 is used to convert the user's natural language question into Python code that is then executed. After computation, the executed code and the answer are displayed to the user. Some LLMs can be vulnerable to prompt injection attacks, where malicious user inputs cause the models to perform unexpected behavior. In this incident, the actor explored several prompt-override avenues, producing code that eventually led to the actor gaining access to the application host system's environment variables and the application's GPT-3 API key, as well as executing a denial of service attack. As a result, the actor could have exhausted the application's API query budget or brought down the application. After disclosing the attack vectors and their results to the MathGPT and Streamlit teams, the teams took steps to mitigate the vulnerabilities, filtering on select prompts and rotating the API key.

Why it relates: The publicly available Streamlit application MathGPT (https://mathgpt.streamlit.app/) uses GPT-3, a large language model (LLM), to answer user-generated math questions. The relevant category is Availability Abuse: An attacker disrupts access to an AI model, agent, or service through resource exhaustion, performance degradation, or an outage.

The publicly available Streamlit application MathGPT (https://mathgpt.streamlit.app/) uses GPT-3, a large language model (LLM), to answer user-generated math questions. Recent studies and experiments have shown that LLMs such as GPT-3 show poor performance when it comes to performing exact math directly. However, they can produce more accurate answers when asked to generate executable code that solves the question at hand. In the MathGPT application, GPT-3 is used to convert the user's natural language question into Python code that is then executed. After computation, the executed code and the answer are displayed to the user. Some LLMs can be vulnerable to prompt injection attacks, where malicious user inputs cause the models to perform unexpected behavior. In this incident, the actor explored several prompt-override avenues, producing code that eventually led to the actor gaining access to the application host system's environment variables and the application's GPT-3 API key, as well as executing a denial of service attack. As a result, the actor could have exhausted the application's API query budget or brought down the application. After disclosing the attack vectors and their results to the MathGPT and Streamlit teams, the teams took steps to mitigate the vulnerabilities, filtering on select prompts and rotating the API key.

SecureFlow · Read the full case ↗

Validated Research · · Practical overlap

MCP Python SDK: Task IDs Cross the Session Ownership Boundary

The MCP Python SDK connects AI applications to tools and supports experimental long-running tasks. When a multi-client server enabled the affected default task handlers, another client could list tasks, read results and cancel work without a task-owner check. CVE-2026-52870 was fixed for default generated task IDs in 1.27.2; explicitly supplied IDs and direct TaskStore writes need separate ownership review.

Why it relates: Unauthorized cancellation can stop another client's work. The demonstrated availability boundary is individual task cancellation, not platform-wide exhaustion or an outage.

Experimental MCP task handlers cross client-session ownership; the default-ID patch does not establish custom-store isolation.

AIA · Read the full case ↗ · SecureFlow · Read the full case ↗

Exercise ·

Microsoft Azure Service Disruption

The Microsoft AI Red Team performed a red team exercise on an internal Azure service with the intention of disrupting its service. This operation had a combination of traditional ATT&CK enterprise techniques such as finding valid account, and exfiltrating data -- all interleaved with adversarial ML specific steps such as offline and online evasion examples.

Why it relates: The Microsoft AI Red Team performed a red team exercise on an internal Azure service with the intention of disrupting its service. The relevant category is Availability Abuse: An attacker disrupts access to an AI model, agent, or service through resource exhaustion, performance degradation, or an outage.

The Microsoft AI Red Team performed a red team exercise on an internal Azure service with the intention of disrupting its service. This operation had a combination of traditional ATT&CK enterprise techniques such as finding valid account, and exfiltrating data -- all interleaved with adversarial ML specific steps such as offline and online evasion examples.

SecureFlow · Read the full case ↗

Incident ·

Exposed LLM Backends Are Becoming Attacker AI Compute

Zenity's honeypots saw operators point autonomous agents and LLM clients at exposed Ollama (a local LLM serving runtime) and LiteLLM (an AI gateway for routing LLM requests) backends. The defender's model server did not have to be exploited with malware; being reachable, unauthenticated, or protected only by a placeholder key was enough to turn it into attacker-funded inference infrastructure.

Why it relates: Zenity Labs observed three distinct operators use exposed Ollama or LiteLLM endpoints between March and May 2026 without exploiting the server software. The relevant category is Availability Abuse: An attacker disrupts access to an AI model, agent, or service through resource exhaustion, performance degradation, or an outage. An open inference service supplies unauthorized compute; the operators' attempted external attacks and lack of confirmed outcomes remain separate.

Zenity Labs observed three distinct operators use exposed Ollama or LiteLLM endpoints between March and May 2026 without exploiting the server software. One sent a 140,000-character Strix prompt and actively retried against a live French auction site before Zenity blocked completion; one staged HexStrike AI with 150 tool definitions but assigned no live target; and one sent 18 Codex-shaped requests carrying an anti-safety web-auditor persona that Zenity assessed as manual web reverse-engineering work without a confirmed target. The flow preserves those different evidence bounds instead of forcing all three into one impact path.

AIA · Read the full case ↗ · SecureFlow · Read the full case ↗