#code + #security

We did not enable internet access or inter-agent communication for many of the environments in these training experiments. Despite these restrictions, the agents discovered ways to exploit our research infrastructure to communicate with one another and access the internet.

The models first found ways to communicate by writing files into the Artifactory package manager. This effectively turned Artifactory into an unintended message board, where agents could exchange information with one another. Read more: How agents used the message board 

The agents also found ways to get access to the internet. Using an exploit⁠(opens in a new window), the agents made Artifactory, which itself had access to the internet for the limited purpose of downloading and installing packages, send any internet requests on their behalf. After the agents discovered these methods for obtaining internet access, they also shared them with other agents through the message board, which provided information to enable additional agents to exploit our infrastructure.

Microsoft Threat Intelligence identified a large-scale npm supply chain attack affecting more than 400 packages across multiple unrelated publishers, including packages associated with major enterprise software ecosystems such as keyv, flat-cache, cache-manager, and others. The malicious releases contain a Mini Shai-Hulud variant, a self-propagating credential-stealing worm delivered through a large, heavily obfuscated Bun-based JavaScript payload. The malware typically executes automatically through an npm preinstall lifecycle hook before package installation completes.

Once executed, the malware searches developer workstations and continuous integration and continuous delivery (CI/CD) environments for npm, GitHub, cloud, and infrastructure credentials. It uses recovered identities to authenticate to npm, GitHub, Amazon Web Services (AWS), Kubernetes, and HashiCorp Vault, enabling it to enumerate packages, repositories, workflow secrets, cloud parameters, and secret-store values. Collected data is encrypted and transmitted through an attacker-controlled HTTPS endpoint, with GitHub repositories serving as a fallback exfiltration channel.

The payload’s most significant capability is automated propagation. After obtaining an npm publishing token, it enumerates packages available to the compromised identity, downloads their latest tarballs, inserts the malware and setup loader, adds a preinstall hook, increments the patch version, and republishes the modified packages. The malware can also use stolen GitHub credentials to inject Claude and Visual Studio Code configuration files into repositories, establishing persistence and creating an additional developer-to-developer infection path.

In this blog, we’re sharing our analysis of this supply chain attack, along with protection, detection, amd hunting guidance. Organizations that installed an affected package with lifecycle scripts enabled should treat the associated developer workstation or build runner as potentially compromised. Investigations should prioritize credentials accessible to the affected identity, unauthorized npm releases, unexpected repository or workflow modifications, suspicious cloud and secret-store access, and artifacts produced by affected build systems. Organizations should revoke and rotate exposed credentials from a known-clean environment and rebuild affected systems and downstream artifacts from trusted sources.

Evidence points towards stolen maintainer credentials as the attack vector for initial compromise. Later propagation used stolen npm publishing tokens and, in targeted workflows, GitHub Actions OIDC publishing access.

• One worm took twelve unrelated organisations between 09:35 and 13:18 UTC on 4 August 2026, each republishing its whole namespace within seconds.

• The confirmed footprint is 2,234 poisoned versions across 444 package names. latest still resolves to a poisoned version on most affected names, so upgrading is not a fix. The maintainers have since cleaned the keyv and cacheable family and unpublished its poisoned releases, which does not help a lockfile pinned while they were live.

• Every poisoned release adds "preinstall": "node setup.mjs", which runs on a bare npm install. Disable install scripts in CI, and treat any npm token used in CI during the window as compromised.

• The payload steals GitHub, npm, AWS, GCP, Azure, Stripe, Vault and Kubernetes credentials, scrapes GitHub Actions runner memory, and can republish packages with valid SLSA provenance.

• It installs a dead-man’s switch that polls GitHub with the stolen token and executes a handler when that token is revoked. Hunt it before rotating anything, because rotation is the trigger.

• Poisoned packages include the auth libraries @or-sdk/auth, @or-sdk/api-tokens, @or-sdk/permissions and @arv-bedrock/auth. The @ornikar packages are mostly lint and build configs, which land on CI runners and developer laptops as dev dependencies.

• There is no C2 host. Exfiltration rides GitHub dead-drop repositories and Actions artifacts under RSA-4096 encryption, and stage one pulls its runtime from the official Bun releases, so no attacker domain appears at either stage.

• 546 dead-drop repositories described Shai-Hulud: Here We Go Again appeared on 4 August 2026, and the same marker appears on the TanStack compromise dated 11 May 2026.

• The keyv repository also ships .claude/settings.json and .vscode/tasks.json hooks that execute when the project opens in an IDE or agent session. Both are still on main.

• The commit that added those hooks shows as verified by GitHub with its author spoofed to github-actions[bot], and the poisoned keyv release carries intact OIDC and SLSA attestation. Trust neither signal here.

1Password for Claude lets you authorize Claude to complete browser-based tasks that require an account login. This is useful for things like booking travel or managing online accounts.

According to 1Password, approved credentials are delivered through a secure channel and injected directly into the destination page. The password, one-time code, and other secrets never enter Claude’s context, memory, or Anthropic’s systems.

Instead of granting ongoing access to a vault, Claude requests the specific login items it needs for a task. The user can approve or deny that request with a biometric prompt, and the permission lasts only for the current session.

1Password can also broker access across multiple websites during the same task, allowing Claude to complete a multi-step workflow without stopping for a new login each time.

The launch also introduces what 1Password calls Agentic Mode.

When a compatible AI agent takes control of the browser, the 1Password extension automatically locks down the vault so that only the credentials explicitly approved for that task remain available.

It requires the 1Password desktop app and browser extension, along with the Claude desktop app and browser extension.

Support for payment cards and identity information is planned for a later update.

The Anthropic partnership was first outlined in March, when 1Password said Claude would gain consent-based access to vault items.

The OWASP GenAI Security Project is a global, open-source initiative dedicated to identifying, mitigating, and documenting security and safety risks associated with generative AI technologies, including large language models (LLMs), agentic AI systems, and AI-driven applications.

Three versions of the durabletask PyPI package (1.4.1, 1.4.2, 1.4.3), Microsoft’s Durable Task SDK for Python, were published on May 19, 2026 using a compromised PyPI API token.

The dropper downloads a stage-2 Python zipapp (rope.pyz) from attacker infrastructure and executes it with all output suppressed. The stage-2 is a full credential harvesting framework with dedicated collectors for AWS Secrets Manager and SSM Parameter Store, Azure Key Vault, GCP Secret Manager, Kubernetes secrets (across all contexts), HashiCorp Vault, and local password managers (1Password, Bitwarden, pass, gopass). It also reads over 90 sensitive files from disk, exfiltrates everything encrypted with RSA-4096/AES-256-GCM to a C2 server, and propagates itself to other hosts via AWS SSM SendCommand and kubectl exec.

The payload includes geopolitical targeting: it skips systems with a Russian locale and contains a destructive rm -rf /* routine targeting Israeli and Iranian systems.

Password Managers (collectors/passwords.py): Attempts to unlock 1Password, Bitwarden, pass, and gopass by brute-forcing passwords harvested from environment variables matching PASS, SECRET, KEY, BW_, OP_, _MASTER patterns, and from shell history (.bash_history, .zsh_history). On success, it dumps every item from every vault.

Filesystem (collectors/filesystem.py): Reads 90+ files including SSH keys, cloud credentials, Docker configs, npm/PyPI/Cargo/Gem tokens, kubeconfig, Terraform state files, VPN configurations (Tailscale state, WireGuard configs), MCP server configs (Claude Desktop, Cursor, VS Code, Zed, Codeium, Continue), and all .env files found under the home directory. Also extracts environment variables from all Docker containers via the Docker socket or CLI, and collects GitHub tokens via gh auth token.

and collects GitHub tokens via gh auth token.

For each token found, it creates a new public repository named with random Slavic folklore words (e.g., BABA-YAGA-KOSCHEI-742, description: “PUSH UR T3MPRR”) and uploads the encrypted data bundle as results.json. The attacker can later search GitHub for repositories matching these distinctive naming patterns to retrieve the exfiltrated data.

1. No trusted publishers. The project uses legacy API token authentication instead of PyPI’s OIDC trusted publisher mechanism. Trusted publishers bind publishing to a specific GitHub repository, workflow, and environment. A stolen token cannot publish from outside that workflow. This project has no such binding: anyone holding the token can upload any version from any machine.

Kubernetes (collectors/kubernetes.py): Parses kubeconfig (with a custom YAML parser, no PyYAML dependency), iterates every context, and dumps secrets from all namespaces. Supports in-cluster service account tokens, client certificate auth, and bearer tokens. If kubectl is not present, the collector downloads it from dl.k8s.io. After collecting secrets, it propagates the payload to up to 5 other running pods via kubectl exec.

To measure the adversarial robustness of AI agents, we introduce AgentDojo, an evaluation framework for agents that execute tools over untrusted data. To capture the evolving nature of attacks and defenses, AgentDojo is not a static test suite, but rather an extensible environment for designing and evaluating new agent tasks, defenses, and adaptive attacks. We populate the environment with 97 realistic tasks (e.g., managing an email client, navigating an e-banking website, or making travel bookings), 629 security test cases, and various attack and defense paradigms from the literature. We find that AgentDojo poses a challenge for both attacks and defenses: state-of-the-art LLMs fail at many tasks (even in the absence of attacks), and existing prompt injection attacks break some security properties but not all. We hope that AgentDojo can foster research on new design principles for AI agents that solve common tasks in a reliable and robust manner.

ChatGPT can directly run Bash commands now. Previously it was limited to Python code only, although it could run shell commands via the Python subprocess module. It has Node.js and can run JavaScript directly in addition to Python. I also got it to run “hello world” in Ruby, Perl, PHP, Go, Java, Swift, Kotlin, C and C++. No Rust yet though! While the container still can’t make outbound network requests, pip install package and npm install package both work now via a custom proxy mechanism. ChatGPT can locate the URL for a file on the web and use a container.download tool to download that file and save it to a path within the sandboxed container.

Is this a data exfiltration vulnerability though? Could a prompt injection attack trick ChatGPT into leaking private data out to a container.download call to a URL with a query string that includes sensitive information?

I don’t think it can. I tried getting it to assemble a URL with a query string and access it using container.download and it couldn’t do it. It told me that it got back this error:

ERROR: download failed because url not viewed in conversation before. open the file or url using web.run first.

This looks to me like the same safety trick used by Claude’s Web Fetch tool: only allow URL access if that URL was either directly entered by the user or if it came from search results that could not have been influenced by a prompt injection.