Unauthenticated directory creation via unvalidated save paths
Published Aug 30, 2026 · Updated Aug 30, 2026
Path injection in Browser Use Web UI 2.0.0 through 3.0.0 allows remote attackers to create arbitrary directories through Gradio. The run_agent_task function passes four attacker-controlled save paths directly to os.makedirs without normalization, allowlisting, or containment validation. The unauthenticated interface reaches these calls before LLM initialization, so no valid API key is needed and container write permissions bound the result.
Summary
What happened
Path injection in Browser Use Web UI 2.0.0 through 3.0.0 allows remote attackers to create arbitrary directories through Gradio. The run_agent_task function passes four attacker-controlled save paths directly to os.makedirs without normalization, allowlisting, or containment validation. The unauthenticated interface reaches these calls before LLM initialization, so no valid API key is needed and container write permissions bound the result.
The record
- CVE
- CVE-2026-82637
- Published
- Aug 30, 2026
- Updated
- Aug 30, 2026
- Vendor
- Browser Use
- Product
- Browser Use Web UI
- Classifications
- CWE-73
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 30, 2026CVE publishedPublication date reported by the CVE source.
- Aug 30, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=2.0.0 <=3.0.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GitHub Issue #737 curl proof of conceptfunctional · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo