Unauthorized tool actions via concealed MCP arguments
Published Feb 10, 2026 · Updated Feb 10, 2026
UI safety failure in Zed before 0.219.4 allows remote authenticated users to conceal malicious MCP tool parameters from users. The MCP tool-call approval and chat-history interfaces omit argument values before and after invocation, preventing inspection of attacker-controlled parameters. Exploitation requires indirect prompt injection from a malicious MCP server and a tool call; manual confirmation still exposes the concealed action, while autoconfirmation also hides its record.
Summary
What happened
UI safety failure in Zed before 0.219.4 allows remote authenticated users to conceal malicious MCP tool parameters from users. The MCP tool-call approval and chat-history interfaces omit argument values before and after invocation, preventing inspection of attacker-controlled parameters. Exploitation requires indirect prompt injection from a malicious MCP server and a tool call; manual confirmation still exposes the concealed action, while autoconfirmation also hides its record.
The record
- CVE
- CVE-2026-25805
- Published
- Feb 10, 2026
- Updated
- Feb 10, 2026
- Vendor
- Zed Industries
- Product
- Zed
- Classifications
- CWE-356
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Feb 10, 2026CVE publishedPublication date reported by the CVE source.
- Feb 10, 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=< 0.219.4
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 advisory MCP tool-poisoning proof of conceptproof of concept · unverified
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