CVE-2026-50548 — Cursor Path Traversal in Agent Sandbox Working Directory
Cursor is a code editor built for programming with AI. Prior to 3.0, Cursor runs agent terminal commands in a sandbox by default, and the sandbox grants write access to the command's working directory. A flaw was identified in how the agent could modify the working_directory parameter, which could cause the sandbox to include writable paths outside the intended workspace. A malicious agent could set working_directory to a sensitive location and write arbitrary files outside the workspace under the user's privileges. This enables non-sandboxed Remote Code Execution — for example by overwriting the cursorsandbox helper so later commands run unsandboxed — with no user interaction beyond a benign prompt. This vulnerability is fixed in 3.0.
Who exploits it and how urgent it is
A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.
How the score was calculated
- EPSS 1% (30-day exploitation probability)+9
- Technical severity (critical)+10
- Automatable exploitation (SSVC)+3
The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).
Triage
Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.
CISA SSVC assessment CISA
Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.
Remediation
Fixes and mitigations documented by the sources — linked to the original advisory.
No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.
First 24 hours
Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.
- Identify exposed assets running the affected vendor/product/version combinations (Anysphere Cursor, Cursor Cursor).
- The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
- No fix documented in the sources: reduce exposure and monitor the vendor advisory.
- Search available logs for exploit probes matching the vulnerability class (file handling), errors and authentication anomalies.
Affected scope
Vendor, product and versions as the sources word them.
Attack characteristics
The CVSS vector, decoded. It describes the attack, not your exposure to it.
Every base score collected
Sources score independently and may disagree; each row says who scored it and under which version.
| Score | Version | Severity | Expl. | Impact | Scored by |
|---|---|---|---|---|---|
| 9.3 | CVSS 4.0 | Critical | — | — | security-advisories@github.com via NIST National Vulnerability Database |
| 9.3 | CVSS 4.0 | Critical | — | — | GitHub_M via CVE Program (cve.org) e CISA ADP |
| 9.8 | CVSS 3.1 | Critical | 3.9 | 5.9 | nvd@nist.gov via NIST National Vulnerability Database |
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H (score shown at the top: nvd@nist.gov) Weakness MITRE
Weakness class according to MITRE’s CWE catalog.
EPSS over time FIRST
Oct 13, 2026 → Oct 15, 2026 · 3 reading(s) · max 1.01%
Detection
Read off the CVSS vector and the weakness class. Starting points, not tested rules.
- Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
- Monitor file creation in web directories and paths with traversal sequences (../).
Analysis and videos
CVE-2026-50548: Cursor Path Traversal in Agent Sandbox Working Directory
CVE-2026-50548 is a path traversal weakness (CWE-22) in Cursor versions before 3.0, where the sandbox used for agent terminal commands can include writable paths outside the intended workspace. According to the record, this could let a malicious agent write files outside the workspace with the user's privileges and lead to non-sandboxed remote code execution. NVD scores it CVSS 3.1 9.8 (Critical), the record says it is fixed in 3.0, and no confirmed exploitation appears in the sources consulted.
Timeline
What happened to this CVE, newest first.
- 2026
- Affected products added · cursor/cursor
- SSVC assessment updated
- Record published
- CVSS changed · 9.8
- Source status changed · → Analyzed
- Record created in this database
- CVE published
Source activity
Repeated readings are counted rather than listed.
- 1× Official description updated · Oct 13, 2026 – Oct 13, 2026
References
1 on the record
Elsewhere on this site
Related CVEs (same products)
- High CVE-2026-73218 Cursor: Sandbox escape via launching privileged containers Aug 11, 2026
- High CVE-2026-73217 Cursor: Sandbox escape via tampered Python virtual environments Aug 11, 2026
- High CVE-2026-63093 Cursor for Windows 3.2.16 RCE via Malicious git.exe in Workspace Jul 17, 2026
- High CVE-2026-61613 Cursor: Cloud Agent Browser Sandbox Escape Jul 15, 2026
- Critical CVE-2026-50549 Anysphere Cursor Link Following Flaw Allows Out-of-Workspace File Writes Jun 25, 2026
- High CVE-2026-48124 Cursor Desktop sandbox escape via Claude hook configuration Jun 15, 2026
Not in any source we poll
Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.
- No fixed version, patch or mitigation documented.
- No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
- No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
- No exploit packet captures, log samples, or incident case IDs supplied.
Answered from this record
Text assembled only from the fields above — no additional claims.
What should defenders know first?
CVE-2026-50548 is "Cursor Path Traversal in Agent Sandbox Working Directory", rated Critical. It affects Cursor (Anysphere); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 9.8 describes technical severity. EPSS 1.01% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.
Comments
Moderated technical discussion. Read the community guidelines.
No comments yet.
Sign in or create an account to comment and suggest corrections.