boxscore/security
CVE · referencelatest edition

Reference page — cumulative record through Thursday, November 19, 2026 UTC. Reference pages update as the archive grows; only dated daily editions are immutable pages of record.

CVE-2026-29783

GitHub Copilot CLI allows for dangerous shell expansion patterns that enable arbitrary command execution
  AV  AC  AT  PR  UI  VC  VI  VA   CVSS    EPSS   %ile   KEV
   N   L   P   N   A   H   H   H    7.5   .0047   41.3     —
AFFECTED
  Product      Versions      Fixed
  copilot-cli  <= 0.0.422 –  —
TIMELINE
  Mar 4   Reserved by GitHub_M
  Mar 6   Published (CNA: GitHub_M)
  Nov 3   EXPLOIT PUBLISHED — CVE-2026-29783 (github copilot-cli). Public exploit reference added.
CWE-78 · CNA: GitHub_M · CVSS v4.0 · 2 references · NVD status: Analyzed

Description

The shell tool within GitHub Copilot CLI versions prior to and including 0.0.422 can allow arbitrary code execution through crafted bash parameter expansion patterns. An attacker who can influence the commands executed by the agent (e.g., via prompt injection through repository files, MCP server responses, or user instructions) can exploit bash parameter transformation operators to execute hidden commands, bypassing the safety assessment that classifies commands as "read-only." This has been patched in version 0.0.423. The vulnerability stems from how the CLI's shell safety assessment evaluates commands before execution. The safety layer parses and classifies shell commands as either read-only (safe) or write-capable (requires user approval). However, several bash parameter expansion features can embed executable code within arguments to otherwise read-only commands, causing them to appear safe while actually performing arbitrary operations. The specific dangerous patterns are ${var@P}, ${var=value} / ${var:=value}, ${!var}, and nested $(cmd) or <(cmd) inside ${...} expansions. An attacker who can influence command text sent to the shell tool - for example, through prompt injection via malicious repository content (README files, code comments, issue bodies), compromised or malicious MCP server responses, or crafted user instructions containing obfuscated commands - could achieve arbitrary code execution on the user's workstation. This is possible even in permission modes that require user approval for write operations, since the commands can appear to use only read-only utilities to ultimately trigger write operations. Successful exploitation could lead to data exfiltration, file modification, or further system compromise.

Lifecycle

Complete event history — 3 events, chronological
DateEventDetail
March 4, 2026ReservedReserved by GitHub_M
March 6, 2026PublishedPublished (CNA: GitHub_M)
November 3, 2026EXPLOIT PUBLISHEDEXPLOIT PUBLISHED — CVE-2026-29783 (github copilot-cli). Public exploit reference added.

Affected

Affected products and packages — 1 row
VendorProduct / PackageEcosystemVersion introducedFixed
githubcopilot-cli—<= 0.0.422—

Weaknesses

CWE-78

References (2)

Related

Authoritative record: CVE-2026-29783 at cve.org

Vendors: github

Weaknesses: CWE-78

About this page

This is a reference page, not a dated page of record. It assembles the complete lifecycle of CVE-2026-29783 from the CVE Program record, NVD enrichment, the CISA KEV catalog, EPSS, and OSV advisories. The box score's numbers (CVSS, EPSS, KEV status) are current as of Thursday, November 19, 2026 UTC and are re-derived as the archive grows; only dated daily editions are immutable pages of record. The authoritative source for this identifier is cve.org.