threatdeck
Live 13:45 UTC ·

OWASP LLM

LLM03 · Supply Chain

Compromised models, datasets, packages, plugins or hosting introduce vulnerabilities or backdoors.

OWASP Top 10 for LLM Applications (2025)

Mitigations

  • Scan model files (pickle) and pin hashes
  • Vet publishers of models, MCP servers and skills
  • Maintain an AI-BOM

Detections 8

Related techniques

In the news

  1. Attacks on AI Research The Decoder High

    Security researchers show how cheap AI inference providers steal keys and snoop on users

    Dragos researchers found compromised cheap AI inference providers on OpenRouter stealing AWS keys and reading customer requests, prompting removal of three providers and 125 endpoints.

    ReviewAudit use of cheap AI inference resellers and rotate any AWS keys sent through them

    LLM03AML.T0010 #ai-supply-chain#api-keys#openrouter 3 min read Brief In your stack
  2. Attacks on AI Vulnerability Zero Day Initiative: published advisories Medium

    ZDI-26-1031: (0Day) LiteLLM MCP Command Injection Remote Code Execution Vulnerability

    ZDI disclosed an authenticated command injection flaw enabling remote code execution in LiteLLM, an LLM gateway (CVSS 7.2).

    ReviewCheck LiteLLM deployments and await vendor patch

    LLM03 #litellm#llm#command-injection Brief In your stack
  3. Attacks on AI Malware Wiz Blog Critical

    Microsoft agent-framework Compromised: Credential Stealer Targets Azure and CI Pipelines

    Versions 1.26.1 and 1.26.2 of Microsoft's agent-framework PyPI package were published with a credential stealer targeting Azure and CI pipelines; they were quarantined.

    HuntHunt for agent-framework 1.26.1/1.26.2 installs in CI pipelines and rotate exposed Azure credentials

    LLM03ASI04 #supply-chain#pypi#credential-theft 4 min read 4 sources 3 IOCs Brief In your stack
  4. Attacks on AI Breach Security Affairs High

    Fireworks AI Breach Exposes Uber Data and Highlights Supply Chain Risks

    Attackers used compromised credentials of Fireworks AI, a technology provider, to access Uber's account and steal data of nearly 150,000 users.

    ReviewReview third-party vendor access and credential hygiene for AI service providers

    LLM03 #supply-chain#credentials#data-breach 4 min read Brief In your stack
  5. Attacks on AI Breach Dark Reading High

    Cursor Traces Malicious Claude Code Extension to Third-Party Breach

    Cursor says threat actors used a compromised key issued to AI infrastructure provider Fireworks to access Cursor data and credentials, tracing a malicious Claude Code extension to the breach.

    ReviewReview Cursor and Claude Code extension usage and rotate credentials tied to affected integrations

    LLM03 #supply-chain#ai-tools#credentials In your stack
  6. Attacks on AI Vulnerability BleepingComputer Medium

    Researchers hijack Hugging Face account for popular Kokoro AI model

    Researchers took over an abandoned Hugging Face account that hosted the popular Kokoro text-to-speech model, exploiting weak ownership verification on the platform.

    MitigateVerify model sources and pin Kokoro downloads to trusted repositories

    LLM03AML.T0010 #hugging-face#model-hub#supply-chain Brief In your stack
  7. Attacks on AI Breach SecurityWeek High

    Cursor Supply Chain Attack Started at Fireworks AI

    Attacker stole an access key from Fireworks AI and used it to exfiltrate credentials, enabling malicious copies of a Claude Code extension to be pushed in a Cursor supply chain attack.

    ReviewCheck whether Cursor or Claude Code extensions in use match malicious copies and rotate exposed credentials

    LLM03ASI04 #supply-chain#ai-coding-tools#credentials Brief In your stack
  8. Attacks on AI Breach SecurityWeek High

    Uber Data Breach Impacts 150,000 People

    Hackers compromised a third-party services provider and stole names, addresses and driver's license numbers of about 150,000 Uber users.

    ReviewReview third-party access and rotate any shared internal credentials

    LLM03 #breach#data-theft#third-party 3 sources Brief In your stack

Tools

Test or exercise it

Detect or mitigate it

Mappings are AI-assisted and checked against the framework definitions; corrections welcome.

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.