Over 30 safety vulnerabilities have been disclosed in numerous synthetic intelligence (AI)-powered Built-in Growth Environments (IDEs) that mix immediate injection primitives with official options to attain information exfiltration and distant code execution.
The safety shortcomings have been collectively named IDEsaster by safety researcher Ari Marzouk (MaccariTA). They have an effect on standard IDEs and extensions equivalent to Cursor, Windsurf, Kiro.dev, GitHub Copilot, Zed.dev, Roo Code, Junie, and Cline, amongst others. Of those, 24 have been assigned CVE identifiers.
“I feel the truth that a number of common assault chains affected each AI IDE examined is essentially the most stunning discovering of this analysis,” Marzouk instructed The Hacker Information.
“All AI IDEs (and coding assistants that combine with them) successfully ignore the bottom software program (IDE) of their menace mannequin. They deal with their options as inherently protected as a result of they have been there for years. Nevertheless, when you add AI brokers that may act autonomously, the identical options will be weaponized into information exfiltration and RCE primitives.”
At its core, these points chain three completely different vectors which are widespread to AI-driven IDEs –
- Bypass a big language mannequin’s (LLM) guardrails to hijack the context and carry out the attacker’s bidding (aka immediate injection)
- Carry out sure actions with out requiring any consumer interplay through an AI agent’s auto-approved device calls
- Set off an IDE’s official options that permit an attacker to interrupt out of the safety boundary to leak delicate information or execute arbitrary instructions
The highlighted points are completely different from prior assault chains which have leveraged immediate injections together with susceptible instruments (or abusing official instruments to carry out learn or write actions) to change an AI agent’s configuration to attain code execution or different unintended conduct.
What makes IDEsaster notable is that it takes immediate injection primitives and an agent’s instruments, utilizing them to activate official options of the IDE to end in info leakage or command execution.
Context hijacking will be pulled off in myriad methods, together with by way of user-added context references that may take the type of pasted URLs or textual content with hidden characters that aren’t seen to the human eye, however will be parsed by the LLM. Alternatively, the context will be polluted through the use of a Mannequin Context Protocol (MCP) server by way of device poisoning or rug pulls, or when a official MCP server parses attacker-controlled enter from an exterior supply.
A few of the recognized assaults made attainable by the brand new exploit chain is as follows –
- CVE-2025-49150 (Cursor), CVE-2025-53097 (Roo Code), CVE-2025-58335 (JetBrains Junie), GitHub Copilot (no CVE), Kiro.dev (no CVE), and Claude Code (addressed with a safety warning) – Utilizing a immediate injection to learn a delicate file utilizing both a official (“read_file”) or susceptible device (“search_files” or “search_project”) and writing a JSON file through a official device (“write_file” or “edit_file)) with a distant JSON schema hosted on an attacker-controlled area, inflicting the information to be leaked when the IDE makes a GET request
- CVE-2025-53773 (GitHub Copilot), CVE-2025-54130 (Cursor), CVE-2025-53536 (Roo Code), CVE-2025-55012 (Zed.dev), and Claude Code (addressed with a safety warning) – Utilizing a immediate injection to edit IDE settings information (“.vscode/settings.json” or “.concept/workspace.xml”) to attain code execution by setting “php.validate.executablePath” or “PATH_TO_GIT” to the trail of an executable file containing malicious code
- CVE-2025-64660 (GitHub Copilot), CVE-2025-61590 (Cursor), and CVE-2025-58372 (Roo Code) – Utilizing a immediate injection to edit workspace configuration information (*.code-workspace) and override multi-root workspace settings to attain code execution
It is price noting that the final two examples hinge on an AI agent being configured to auto-approve file writes, which subsequently permits an attacker with the flexibility to affect prompts to trigger malicious workspace settings to be written. However on condition that this conduct is auto-approved by default for in-workspace information, it results in arbitrary code execution with none consumer interplay or the necessity to reopen the workspace.
With immediate injections and jailbreaks performing as step one for the assault chain, Marzouk gives the next suggestions –
- Solely use AI IDEs (and AI brokers) with trusted tasks and information. Malicious rule information, directions hidden inside supply code or different information (README), and even file names can turn out to be immediate injection vectors.
- Solely hook up with trusted MCP servers and repeatedly monitor these servers for modifications (even a trusted server will be breached). Evaluate and perceive the information circulate of MCP instruments (e.g., a official MCP device would possibly pull info from attacker managed supply, equivalent to a GitHub PR)
- Manually evaluation sources you add (equivalent to through URLs) for hidden directions (feedback in HTML / css-hidden textual content / invisible unicode characters, and so forth.)
Builders of AI brokers and AI IDEs are suggested to use the precept of least privilege to LLM instruments, reduce immediate injection vectors, harden the system immediate, use sandboxing to run instructions, carry out safety testing for path traversal, info leakage, and command injection.
The disclosure coincides with the invention of a number of vulnerabilities in AI coding instruments that might have a variety of impacts –
- A command injection flaw in OpenAI Codex CLI (CVE-2025-61260) that takes benefit of the truth that this system implicitly trusts instructions configured through MCP server entries and executes them at startup with out searching for a consumer’s permission. This might result in arbitrary command execution when a malicious actor can tamper with the repository’s “.env” and “./.codex/config.toml” information.
- An oblique immediate injection in Google Antigravity utilizing a poisoned net supply that can be utilized to control Gemini into harvesting credentials and delicate code from a consumer’s IDE and exfiltrating the knowledge utilizing a browser subagent to browse to a malicious website.
- A number of vulnerabilities in Google Antigravity that might end in information exfiltration and distant command execution through oblique immediate injections, in addition to leverage a malicious trusted workspace to embed a persistent backdoor to execute arbitrary code each time the applying is launched sooner or later.
- A brand new class of vulnerability named PromptPwnd that targets AI brokers linked to susceptible GitHub Actions (or GitLab CI/CD pipelines) with immediate injections to trick them into executing built-in privileged instruments that result in info leak or code execution.
As agentic AI instruments have gotten more and more standard in enterprise environments, these findings show how AI instruments develop the assault floor of improvement machines, usually by leveraging an LLM’s incapability to tell apart between directions supplied by a consumer to finish a process and content material that it could ingest from an exterior supply, which, in flip, can comprise an embedded malicious immediate.
“Any repository utilizing AI for concern triage, PR labeling, code solutions, or automated replies is prone to immediate injection, command injection, secret exfiltration, repository compromise and upstream provide chain compromise,” Aikido researcher Rein Daelman mentioned.
Marzouk additionally mentioned the discoveries emphasised the significance of “Safe for AI,” which is a brand new paradigm that has been coined by the researcher to deal with safety challenges launched by AI options, thereby making certain that merchandise are usually not solely safe by default and safe by design, however are additionally conceived holding in thoughts how AI elements will be abused over time.
“That is one other instance of why the ‘Safe for AI’ precept is required,” Marzouk mentioned. “Connecting AI brokers to present functions (in my case IDE, of their case GitHub Actions) creates new rising dangers.”
