DOMShell is a Chrome automation project whose MCP server exposes Unix-style tools for AI agents.
CVE-2026-75518
DOMShell is a Chrome automation project whose MCP server exposes Unix-style tools for AI agents. Prior to 2.0.8, the DOMShell MCP server classifies the domshelleval tool and eval command as read-tier operations that can run without --allow-write, even though eval shares the Runtime.evaluate dispatch path with the write-tier js command and has no side-effect gate. An MCP caller with tool-session access can therefore use domshelleval to mutate DOM, window, or global state while the host approval interface, server authorization flags, denial messages, and audit records represent the operation as read-only. The bypass does not expose a capability beyond domshelljs for callers already authorized to write, but it violates the configured permission boundary for callers lacking that authorization. This issue is fixed in version 2.0.8.
Part of the AI stack
This affects Model Context Protocol, in MCP & tool servers.
Assessment
- CVSS
- 4.8 (v4.0)
- Severity
- Medium
- Known exploited
- Not listed in CISA KEV
- Exploit availability
- Nothing found in Exploit-DB, Metasploit, Nuclei or public PoC repositories
- Published
- 18 November 2026
- Last updated
- 18 November 2026
- Assigner
- GitHub_M
CVSS vectorCVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N
At the source
References
Community proofs of concept
No community proof of concept yet. If you have one for a published vulnerability and the right to share it, add it below — it will appear here once reviewed.
Submit a proof of concept
Only for publicly disclosed vulnerabilities, and only material from testing you were authorised to perform. This platform does not buy, sell, or broker exploits — see earning from vulnerability research for legitimate bounty programs. Submissions are reviewed before they appear. Text only; do not include live credentials, personal data, or anything targeting systems you are not permitted to test.
Query this programmatically
Agents can read this through the MCP endpoint, or over HTTP:
curl https://cve.zerocrew.in/api/cve/CVE-2026-75518