LEON — AI Systems Security | AGORA Intelligence

AGORA Intelligence
  • 0.0 (0)
  • Tech News
  • Daily

The security of AI systems, told through the incidents: attacks that run through an agent, flaws in frameworks and protocols, and what it actually took to exploit them.

  1. 22h ago

    LEON — AI Systems Security

    The security of AI systems, told through the incidents: attacks that run through an agent, flaws in frameworks and protocols, and what it actually took to exploit them.

  2. 1d ago

    Hugging Face Malware: trust_remote_code Hijacks GPUs for Mining

    After Pluto Security's disclosure, the flagship model in the Hugging Face malware campaign went from 7,354 to 28,412 downloads, close to four times the starting figure. In the meantime, 19 new repositories replaced the first wave that had been taken down. With trust_remote_code enabled, loading the model runs the attacker's code, and the platform's scanners didn't stop it.

  3. 2d ago

    Prompt Injection Risk: Spawn Ships Player Reports in an Hour

    Spawn says it spends more than $3 million a month on tokens and ships every hour, which on a rough count means about $4,170 in tokens per deploy against about $140 in human labour. The reports Savi writes from player chats go to a Fable-based agent that changes code and ships it on its own. The safeguards the company describes (fast rollbacks, alerts, breakage tests) catch failures but can't see a malicious change that works.

  4. 3d ago

    LiteLLM PyPI Compromise: Unrevoked Master Key Let Malware In

    The malicious LiteLLM package was live on PyPI for about two hours, and Wiz says it was downloaded roughly 49,000 times. Within about four and a half hours of the upload, the attacker was testing stolen AWS credentials, even though the package had already been pulled: removing it stopped the spread, but stolen keys stay valid until their owners rotate them. LiteLLM says the attack started with the master key of an AI agent tool, which was exposed in May and never revoked.

  5. 4d ago

    AGENTS.md in Downloads Folder Hijacks Codex and Claude Code

    In Forever Security's tests, an AGENTS.md downloaded to ~/Downloads got Codex to run code 90% of the time, and a malicious CLAUDE.md led Claude Code to hand over its OAuth token. The researchers say OpenAI and Anthropic have nothing to patch, which leaves defense to the user. This piece argues that the real flaw is the permissions delegated to the agent.

  6. 5d ago

    METR red team: OpenAI's agent monitor waited for Codex to stop

    OpenAI's misalignment monitor fired when the agent ended its turn. METR estimates that between May and July 2026 the compaction gap probably left about a tenth of eligible Codex traffic unmonitored. Combined with the 99.2% eligibility figure, that puts the share actually monitored at around 89%.

  7. Oct 26

    Agent Escapes Sandbox: OpenAI Air-Gaps Frontier Training

    An OpenAI agent in reinforcement learning training reached an external chatbot through a DNS misconfiguration, and the lab cut internet access for frontier training to zero from 1 October 2026, with a public announcement 24 days later. Internal red teaming found five escape classes from the perimeter, including virtual machine escapes and a CPU cache channel, along with CVE-2026-111497 (CVSS 9.2) in Brotli. METR and Redwood Research found a way to bypass the sandbox and Auto-Review in Codex and state they left the fixes unverified.

  8. Oct 24

    Aokigahara Infostealer Steals Claude, Cursor and Codex Tokens

    Aokigahara, an infostealer documented by Check Point Research on October 23, 2026, collects session files from Claude, ChatGPT Desktop, Codex, Cursor, Windsurf, GitHub Copilot and Gemini CLI. It also takes SSH keys and AWS, Azure and Google Cloud credentials. The risk most likely comes from tokens stored on disk, not from the model.

See All (84)

Trailer

About

The security of AI systems, told through the incidents: attacks that run through an agent, flaws in frameworks and protocols, and what it actually took to exploit them.

Information