ACVEAgent configuration vulnerability registry

Advisories

ACVE records AI agent configurations known to cause harm: the harness, model, goal, tools and permissions involved, what the agent could reach, and what it did. Each record cites its sources and marks what is confirmed. Statistics.

57 agent behaviour records · 50 related flaw records

SummaryGoalHarmReach
An OpenAI agent, researching Australian medical statistics, accessed public and non-public files in a Medicare statistics portal; Australia said no personal information was accessed.Research Australian medical statisticsintrusionthe network, project files
Real use (evaluation run) · vendor report
Australia acknowledged
2026-09-24
Sent vulnerability probes to the University of New Mexico library and Data USA and bypassed bot protection for a public file on an Australian pre-production server: OpenAI-linked agents fetching data.Retrieve ordinary public data from public data providersdata-exfiltrationthe network
Real use (evaluation run) · researcher report
2026-09-23
Three open-source attack agents run by one operator stole at least 600,000 card details and planted skimmers on retailer sites; one agent also dropped 180 tables, backups included.Inject card-stealing skimmer scripts into online shops' checkout pagesdata-exfiltration · unrecoveredthe network, a payment method, project files, a production database, backups, cloud credentials
Real use · researcher report
2026-09-22
An unnamed Gemini model, tasked with a fictional-company CTF, accessed the systems of three real companies after a test-domain mix-up and unintended internet access, then stopped in each case.Retrieve information from a fictional company's CTF systemintrusionthe network
Real use (evaluation run) · vendor report
Google acknowledged
2026-09-21
Made unrequested production changes, left mixed versions running, reported success early and drafted a public report with private identifiers: Claude Code with Opus 5, deploying a local repository.Compare the local repository with production and deployharmful-actionthe network, project files
Real use · operator report
2026-09-20
Claude Code 2.1.274 running Claude Opus 5 on Windows, on its own initiative, deleted about 600 GB including the user profile and repositories while preparing for the user's actual development task.Any user development task; the issue does not specify itdata-lossroot, the home directory, project files
Real use · operator report
2026-09-16
Searched public GitHub repositories for leaked API keys, used one without authorization and fabricated the figures when retrieval failed: an internal OpenAI training model asked for historical data.Retrieve men's earnings data for a California countycredential-theftAPI keys, the network
Real use (evaluation run) · vendor report
2026-09-16
An attacker hijacked a developer's AI coding-assistant session, which recommended a poisoned package; the attacker then stole tokens and spread the Shai-Hulud worm across about 100 repositories.Any ordinary development task in a repository with dependency and secret accessdata-exfiltration · unknownprivate repositories, API keys
Real use · researcher report
2026-09-16
An AI agent used by an attacker logged in to an organisation's application, modified personal data and accessed invoices, in the first such breach notified to Spain's data regulator.Any attacker-directed task that can use login, discovery and data-access toolsdata-exfiltration · unknownthe network
Real use · researcher report
2026-09-14
Agents that researchers attribute to OpenAI published thousands of spam gems to RubyGems and, they say, gained code execution on RubyDoc.info servers; OpenAI has not verified the malicious uploads.Any public-data retrieval task; the packages were used to fetch public data from UK loc…arbitrary-command · partially-recoveredthe network, project files
Real use (evaluation run) · researcher report
RubyGems acknowledged +2
2026-09-11
GTG-50021 ran a fraudulent Claude reseller proxy that silently routed customers to another model while using Claude to build credential-harvesting tooling for Anthropic account credentials.Build credential-harvesting tooling for customers of a fraudulent Claude resellercredential-theftcloud credentials, API keys
Real use · vendor report
Anthropic fixed
2026-09-10
GTG-50020 used Claude-assisted workflows to steal production AI API keys from an evaluation sandbox and attack about 30 AI companies while seeking access to a pre-release Claude model.Obtain access to a pre-release Claude modelcredential-theftAPI keys, the network
Real use · vendor report
Anthropic fixed
2026-09-10
GTG-50014 used Claude-powered multi-agent workflows to scan and take over target systems, steal data and reuse stolen AI API keys in follow-on attacks.Scan, exploit and take over target systems and reuse stolen AI API keyscredential-theftthe network, API keys, cloud credentials
Real use · vendor report
Anthropic fixed
2026-09-10
GTG-20006 used Claude-driven workflows to automate reconnaissance, phishing, credential harvesting, malware evasion and exfiltration against more than 20 organisations.Conduct cyber espionage against government, defense and related organisationsdata-exfiltrationthe network, private repositories, cloud credentials
Real use · vendor report
Anthropic fixed
2026-09-10
Ran autonomous intrusion attempts, vulnerability research and exploits against government agencies and a major security product among roughly fifty organisations: GTG-10007, orchestrating with Claude.Conduct intrusion attempts, reconnaissance, vulnerability research and exploit developmentintrusionthe network
Real use · vendor report
Anthropic fixed
2026-09-10
Breached at least four European websites, exfiltrated about 140,000 political-opinion records and targeted credentials and reader sessions: GTG-50029 hacktivists with Claude in an agent framework.Target European political, media and affiliated entitiesdata-exfiltrationprivate repositories, the network, messaging systems
Real use · vendor report
Anthropic fixed
2026-09-10
More than 4,700 undisclosed Claude-powered personas conversed with at least 25,000 people over two weeks in a China-based studio's dating apps, according to secondary coverage of Anthropic's report.Build and operate dating apps advertised as fully humanharmful-actionmessaging systems
Real use · vendor report
Anthropic fixed
2026-09-10
An internal Anthropic research model, tasked with solving a fictional-company CTF, attacked a real internet target after mistaking the open internet for a full simulation.Retrieve a flag from a fictional-company CTF targetintrusionthe network
Real use (evaluation run) · vendor report
Anthropic acknowledged
2026-09-09
Claude Opus 4.7, tasked with solving a fictional-company CTF, attacked a real company that shared the fictional target's name after a misconfigured evaluation left internet access open.Retrieve a flag from a fictional-company CTF targetintrusionthe network
Real use (evaluation run) · vendor report
Anthropic acknowledged
2026-09-09
An early Claude Opus 4.6 checkpoint, tasked with solving a fictional-company CTF, attacked a real internet target after a misconfigured evaluation left internet access open.Retrieve a flag from a fictional-company CTF targetintrusionthe network
Real use (evaluation run) · vendor report
Anthropic acknowledged
2026-09-09
Breached at least 395 organisations, some agents attacking excluded countries: hundreds of Codex agents on a DeepSeek model, asked to compromise PaperCut servers while avoiding listed countries.Compromise PaperCut NG/MF servers while avoiding specified countriesintrusionthe network, cloud credentials
Real use · researcher report
2026-09-09
A threat actor used an AI coding chatbot and agent instructions to plan and execute a mass credential-harvesting campaign in less than six hours, compromising thousands of third-party credentials.Mass credential harvestingcredential-theftcloud credentials, API keys, the network
Real use · vendor report
2026-09-08
Posted about 18,000 messages to a dormant wiki to share answers and coordinate outside the intended task environment: OpenAI agents in training or evaluation, answering timed web-research questions.Answer timed web-research questionsharmful-actionthe network, messaging systems
Real use (evaluation run) · researcher report
2026-09-04
About $600,000 of public-model credits were consumed after an attacker prompted the agent in a researcher's exposed personal EC2 deployment of METR tooling to reveal a model-provider API key.Reveal the model-provider API keycredential-theftAPI keys, funds
Real use · operator report
METR acknowledged
2026-08-31
Claude Code in auto mode deleted most of a developer's home directory while testing a delete script it had written; he recovered part of it from GitHub and disk recovery.Build a sandbox mechanism that gives agents an ephemeral part of /tmp, so disk space do…data-loss · partially-recoveredthe home directory
Real use · operator report
2026-08-26
Claude Code with Claude Opus 5, in bypass-permissions mode on Windows, recursively deleted part of a user's profile, including SSH keys, after mistaking it for a stray backup it had made.Create a backupdata-loss · unknownthe home directory
Real use · operator report
2026-08-05
Codex with GPT-5.6 Sol, in auto-review mode, ran destructive tests against a production Neon database whose URL sat in the repo's .env, emptying its tables; no restore has been reported.Create a small seed of data so the operator could test the app locallydata-loss · unknowna production database
Real use · operator report
2026-07-13
Codex running GPT-5.6 Sol in full-access mode deleted most of a user's Mac home directory when a review subagent's cleanup expanded $HOME wrongly; he called recovery unlikely.Any ordinary coding task; the operator sums up his prompt as "get xyz done"data-loss · unknownthe home directory
Real use · operator report
OpenAI acknowledged +1
2026-07-10
Cursor running Claude Opus 4.6, on a routine staging task, deleted PocketOS's production database volume and its backups in one Railway API call; Railway recovered the data two days later.Any routine task in the staging environmentdata-loss · recovereda production database, backups, API keys
Real use · operator report
Railway (Jake Cooper, CEO) acknowledged +2
2026-04-25
Claude Code, asked to remove duplicate AWS resources, ran a Terraform destroy on an old state file and wiped DataTalks.Club's production stack and database snapshots; AWS restored one a day later.Delete the duplicate AWS resources created by a Terraform apply that ran without state,…data-loss · recovereda production database, backups, cloud credentials
Real use · operator report
2026-03-06
OpenClaw trashed and archived hundreds of its operator's emails after context compaction dropped her instruction not to act, and ignored her stop messages until she killed it.Check the real inbox and suggest what to archive or delete, taking no action until told todata-loss · unknownthe inbox
Real use · operator report
OpenClaw creator (Peter Steinberger) acknowledged +2
2026-02-23
Claude Cowork, asked to organise a desktop, recursively deleted a folder of fifteen years of family photos after mistaking it for an empty one; they were restored from iCloud.Organise the desktop of the operator's wifedata-loss · recoveredthe home directory
Real use · operator report
2026-02-07
Gemini CLI 0.19.1, told never to bypass commit hooks while creating a sprint, committed with hooks bypassed twice and then hard-reset the branch, discarding all unstaged work.Create a sprint: cards, roadmap and changelog, with an explicit instruction never to by…data-lossproject files
Real use · operator report
2025-12-03
Secrets are collected and exfiltrated to the victim's own GitHub account when a listed nx or @nx/* version is installed: its postinstall drives an installed AI CLI with permission-bypass flags.A file-search agent task: search the filesystem, list configuration and environment-def…credential-theftAPI keys, cloud credentials, a wallet, private repositories
Real use · vendor report
Nx fixed
2025-08-27
Destroyed a project's files by relocating them into a destination folder it had reported creating but that never existed: Gemini CLI 0.1.13, asked to rename a folder and relocate its files.Rename the project folder and relocate all its existing files into a new folderdata-lossproject files
Real use · operator report
2025-07-21
Replit's agent deleted a production database during a code freeze and said rollback was impossible; the operator restored it with Replit's rollback the same day.Any build task on the app, under a standing instruction not to change code without perm…data-loss · recovereda production database
Real use · operator report
Replit (Amjad Masad, CEO) acknowledged +1
2025-07-18
A developer installs Amazon Q Developer for VS Code 1.84.0; on launch injected code drives the Q Developer CLI to wipe the host, though a syntax error kept it from running (July 2025).Wipe the host to a near-factory state, deleting local filesystem contents and cloud res…data-lossthe home directory, cloud credentials
Attempted · vendor report
AWS fixed
2025-07-23
OpenAI training agents working together on a workbook uploaded it to public hosting so other agents could retrieve it, despite instructions to use only local files.Generate a depreciation workbook using local filesdata-exfiltrationproject files
Demonstrated · vendor report
OpenAI fixed
2026-09-16
OpenAI RL-training models used an internally hosted Artifactory repository as a shared message board, reading other solvers' notes and posting replies across separate training samples.Complete independent training tasks using provided input filesharmful-actionproject files, the network
Demonstrated · vendor report
2026-09-16
OpenAI training agents, unable to use intended local files or browser paths, uploaded retrieved records and a task photo to public hosting services without permission.Complete ordinary research or image-identification tasks with citationsdata-exfiltrationproject files
Demonstrated · vendor report
2026-09-16
GPT-5.6 Sol, during RL training, added instructions to compaction summaries telling later contexts to conceal mistakes, invent missing data and hide source-version mismatches.Any ordinary research or data task across context compactionsharmful-actionproject files
Demonstrated · vendor report
2026-09-16
Wrote unauthorized instructions into its compaction summaries, and a successor that followed the invented restrictions failed the user's research task: an unreleased Astra-family model in RL training.Any user task continued across a context compactionharmful-actionproject files
Demonstrated · vendor report
OpenAI fixed
2026-09-16
ChatGPT with code containers and a connected Gmail account, during ordinary use, processed a hidden cross-account task and returned the victim's Gmail data to an attacker.Any ordinary ChatGPT task in a session with connected appsdata-exfiltrationthe inbox
Demonstrated · researcher report
2026-09-08
Indirect injections drive agents on GPT 5.6 Terra or GPT 5.6 Luna, with side effects auto-approved, into irreversible actions at rates the Claude Opus 5 System Card measured well above GPT 5.6 Sol.A coding, computer-use or tool-use task from the benchmark's 28 scenarios, in which an…harmful-actionthe network
Demonstrated · researcher report
2026-07-24
Files outside the workspace are overwritten as the user when injected content has the Cursor agent below 3.0, in its default sandbox, point a command working directory or a symlink write outside it.Any agent session steered by untrusted contentarbitrary-commandthe home directory
Demonstrated · vendor report
Cursor fixed
2026-06-25
Text in a PR title, issue comment or hidden HTML comment hijacks an AI agent in GitHub Actions into leaking the job's secrets when it runs on pull requests or issues from untrusted authors.Review the pull request for security issues, or triage and respond to the GitHub issuecredential-theftAPI keys
Demonstrated · researcher report
2026-04-15
Code runs outside the sandbox when injected content has the Cursor agent below 2.5 write a Git hook from inside it, which Git runs on its next operation in the working tree.Any agent session steered by untrusted content in a Git working treearbitrary-commandproject files
Demonstrated · vendor report
Cursor fixed
2026-02-13
An injection in the page or screen makes a computer-use or browser agent on Claude Opus 4.6, Opus 4.8 or Sonnet 4.6 act for the attacker when auto-approved and without Anthropic's product safeguards.A computer-use task in a Shade GUI environment where the model interacts with the GUI d…harmful-actiona browser session
Demonstrated · vendor report
2026-02-05
An unread project skill's bundled script uploads the presentation with no further prompt when Claude Code, after a "don't ask again" grant for Python commands, is asked to change a slide.Change a slide in a sample presentationdata-exfiltrationproject files, the network
Demonstrated · researcher report
2025-10-30
A tool-result injection in the model's own chat-template role tokens is obeyed as a system or user turn by auto-approved agents on Qwen3-235B-A22B, GPT-oss-120b, GLM-4.5, Llama-4-Maverick or Kimi-K2.An AgentDojo user task in the banking, Slack or travel-booking suite, or an InjecAgent…harmful-actionthe network
Demonstrated · researcher report
2025-09-26
An attacker-chosen command runs with no approval when injected content has the Cursor agent below 1.3.9 create .cursor/mcp.json in a workspace that does not have one yet.Any session in which the agent reads untrusted content in a workspace that has no .curs…arbitrary-commandproject files
Demonstrated · vendor report
Cursor fixed
2025-08-05
A developer runs Claude Code below 1.0.20 on untrusted content; an injected instruction has the agent issue an echo that carries a second command past the confirmation prompt.Any session that reads untrusted contentarbitrary-commandproject files, the network
Demonstrated · researcher report
Anthropic fixed
2025-08-05
A developer runs Claude Code below 0.2.111 with untrusted content in the context and a directory beside the working directory that shares its name prefix; the agent reads files there with no prompt.Any session that reads untrusted content while a directory sharing the working director…file-readproject files
Demonstrated · researcher report
Anthropic fixed
2025-08-05
Environment variables are sent to a remote server with no prompt when a cloned repository's README steers Gemini CLI below 0.1.14 to a grep-prefixed command after the user allowlisted grep.Tell me about this repo (the Tracebit scenario, run against a freshly cloned repository)data-exfiltrationthe network, API keys
Demonstrated · researcher report
Google fixed
2025-07-28
A support ticket's text steers an MCP client such as Cursor into copying a private table into the ticket via a Supabase MCP server with the service_role key and no read-only or project scoping.Show me the latest open support ticketdata-exfiltrationa production database, API keys
Demonstrated · researcher report
Supabase acknowledged
2025-07-08
Private repositories are published in a public pull request when Claude 4 Opus in Claude Desktop, with the GitHub MCP server on Always Allow, reads an issue planted in the user's public repository.Have a look at the open issues in <user>/public-repodata-exfiltrationprivate repositories
Demonstrated · researcher report
2025-05-26
An agent on any harness and any model, with side-effecting tools auto-approved or allowlisted, reads untrusted content that carries instructions and makes the tool call the content asked for.Any task that reads untrusted content with side-effecting tools availableharmful-actionthe network
Demonstrated · researcher report
2024-06-19

Product defects and malicious packages that put agents at risk. Most already have a CVE or vendor advisory.