Skip to the content
AI and Cybersecurity Learning and Practice Center Test automation Open the Learning Center

Is my AI tool safe?Coding agentsAnthropic

Is Claude Code safe?

No tool is safe or unsafe on its own: it depends on what it can reach and how it is set up. The record for Claude Code: 17 incidents in this center's library and 12 CVEs in its advisory feed (11 high, 1 medium), the newest published Nov 9, 2026. Below: what went wrong, what was fixed, and how to use it safely.

What to watch for

The most-targeted coding agent in the library: hijacked through GitHub issues, web pages, firewall logs, plugin pins and repository config files, and used by criminals as the hands of an intrusion. Ten CVEs in the feed: most are approval-prompt or write-restriction bypasses, and the newest (June 2026) leaked data through a domain WebFetch trusted.

How to use it safely

Pin the version and update within days of an advisory, run it in a container with restricted egress, keep credentials out of its reach, and review .claude/ files like CI configuration.

What it can reach

  • Reads attacker-controlled content
  • Runs commands with your permissions
  • Holds API keys and tokens
  • Installs plugins, skills or tools from registries

What went wrong: incidents in the library

Known CVEs

  • CVE-2026-88968 High Claude Code Edit tool race lets code in the sandbox write files outside the workspace
    Nov 9, 2026 · fixed in 2.1.251
  • CVE-2026-86063 High Claude Code plugin hash pinning bypassed by a branch named like the pinned commit
    Oct 9, 2026 · fixed in 2.1.179
  • CVE-2026-54316 Medium Claude Code leaks data through a pre-approved domain in WebFetch
    Jun 13, 2026 · fixed in 2.1.163
  • CVE-2026-25723 High Claude Code piped sed command bypasses file write restrictions
    Feb 6, 2026 · fixed in 2.0.55
  • CVE-2026-25722 High Claude Code directory change bypasses write protection
    Feb 6, 2026 · fixed in 2.0.57
  • CVE-2026-24887 High Claude Code find command injection bypasses the approval prompt
    Feb 3, 2026 · fixed in 2.0.72
  • CVE-2025-66032 High Claude Code command validation bypass allows arbitrary code execution
    Dec 3, 2025 · fixed in 1.0.93
  • CVE-2025-59536 High Claude Code runs project commands before the startup trust dialog
    Oct 3, 2025 · fixed in 1.0.111
  • CVE-2025-58764 High Claude Code rg command bypasses the approval prompt
    Sep 10, 2025 · fixed in 1.0.105
  • CVE-2025-54794 High Claude Code path restriction bypass
    Aug 4, 2025 · fixed in 0.2.111
  • CVE-2025-54795 High Claude Code echo command bypasses the approval prompt
    Aug 4, 2025 · fixed in 1.0.20
  • CVE-2025-52882 High Claude Code IDE extension accepts WebSocket connections from any origin
    Jun 23, 2025 · fixed in 1.0.24

How many people use it

A high CVE count can mean heavy scrutiny as much as weak engineering, so read the incidents and advisories, not only the number. The counts are what this center has recorded, not every flaw ever found; usage figures are the vendors' and registries' own published numbers.

Sources

Compare it with the others on the Technology watch list