Arbitrary code execution via misclassified shell expansions
Published Mar 6, 2026 · Updated Mar 6, 2026
OS command injection in GitHub Copilot CLI 0.0.422 and earlier allows attackers to execute arbitrary code through crafted shell-tool input. The shell safety assessor marks commands using read-only utilities as safe without rejecting executable Bash parameter expansions such as @P, assignment, indirection, or nested substitution. Exploitation requires attacker-influenced agent command text from repository content, MCP responses, or instructions and runs with the user's workstation privileges.
Summary
What happened
OS command injection in GitHub Copilot CLI 0.0.422 and earlier allows attackers to execute arbitrary code through crafted shell-tool input. The shell safety assessor marks commands using read-only utilities as safe without rejecting executable Bash parameter expansions such as @P, assignment, indirection, or nested substitution. Exploitation requires attacker-influenced agent command text from repository content, MCP responses, or instructions and runs with the user's workstation privileges.
The record
- CVE
- CVE-2026-29783
- Published
- Mar 6, 2026
- Updated
- Mar 6, 2026
- Vendor
- Product
- GitHub Copilot CLI
- Classifications
- CWE-78, T1059.004
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 6, 2026CVE publishedPublication date reported by the CVE source.
- Mar 6, 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=<= 0.0.422
What conditions does exploitation require?
What is affected?
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 Bash expansion proof of conceptproof of concept · 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