What Happened
Two flaws in Cursor, an AI code editor, could let a single, ordinary-looking prompt break out of the editor's safety sandbox and run any command on a developer's computer. There is no click to fall for and no approval box to ignore. Cato AI Labs found the pair and named them DuneSlide. They are tracked as CVE-2026-50548 and CVE-2026-50549, both rated 9.8 out of 10 (or 9.3
Why It Matters
The report says two Cursor vulnerabilities, CVE-2026-50548 and CVE-2026-50549, let a single prompt cause the agent to escape its terminal sandbox and run commands on the developer’s machine, with fixes released in Cursor 3.0.[1][3][5][6] The described attack path relies on prompt injection delivered through content the agent ingests, such as an MCP server response or web result, and can lead to arbitrary file write and remote code execution under the user’s privileges.[1][3][5] CyberSE.AI would treat this as a high-risk prompt-injection and agent-sandboxing issue that warrants hardening agent command boundaries, auditing business logic around tool use, and continuous red teaming of untrusted-input paths.
CyberSE Analysis
This signal maps to prompt injection. Organizations using AI agents, LLM APIs, SaaS integrations, or sensitive data workflows should review whether this class of issue could create unauthorized tool execution, data leakage, weak approval gates, or unmanaged supply-chain exposure.
Recommended Actions
- Restrict AI agent tool permissions and production write paths.
- Review sensitive data access across prompts, logs, embeddings, memory, and SaaS integrations.
- Add human approval workflows for high-impact or state-changing actions.
- Run prompt injection and indirect prompt injection tests against affected workflows.
- Document the owner, control gap, and remediation deadline for this risk class.
Source
https://thehackernews.com/2026/07/critical-cursor-flaws-could-let-prompt.html