Arbitrary file write from Cursor Agent through a prompt injection from malicious @Docs
Key facts
- Attack vector
- Network
- Privileges required
- Low
- User interaction
- Required
- Attack complexity
- High
- Impact type
- —
- Confidentiality · integrity · availability
- High · High · High
- Fix status
- Fixed
Attack profile from CVSS 3.1 · CNA. Fix status from CNA.
Summary
Cursor is a code editor built for programming with AI. In versions 0.45.0 through 0.48.6, the Cursor app introduced a regression affecting the set of file paths the Cursor Agent is permitted to modify automatically. Under specific conditions, the agent could be prompted, either directly by the user or via maliciously crafted context, to automatically write to files outside of the opened workspace. This behavior required deliberate prompting, making successful exploitation highly impractical in real-world scenarios. Furthermore, the edited file was still displayed in the UI as usual for user review, making it unlikely for the edit to go unnoticed by the user. This vulnerability is fixed in 0.48.7.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- No
- Technical impact
- Total
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
Remediation
- Fix · CNA cursor (getcursor) Fixed in 0.48.7
Timeline
- 2026-10-02 Threatist record created from CVE-2025-32018
More getcursor vulnerabilities
- TI-2024-32616 RCE via Prompt Injection Into Cursor's Terminal Cmd-K CVSS 4.0CRITICAL 9.2
- TI-2025-31230 Cursor Agent Potentially Leaks Information using JSON schema CVSS 3.1MEDIUM 5.9
- TI-2024-30620 TCC Bypass in Cursor's macOS Application CVSS 3.1LOW 3.8
Sources
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences