High severityNVD Advisory· Published Oct 3, 2025· Updated Oct 3, 2025
Claude Code's startup trust dialog could lead to Command Execution attack
CVE-2025-59536
Description
Claude Code is an agentic coding tool. Versions before 1.0.111 were vulnerable to Code Injection due to a bug in the startup trust dialog implementation. Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog. Exploiting this requires a user to start Claude Code in an untrusted directory. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version. This issue is fixed in version 1.0.111.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
@anthropic-ai/claude-codenpm | < 1.0.111 | 1.0.111 |
Affected products
2- Range: < 1.0.111
Patches
Vulnerability mechanics
References
3- github.com/advisories/GHSA-4fgq-fpq9-mr3gghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2025-59536ghsaADVISORY
- github.com/anthropics/claude-code/security/advisories/GHSA-4fgq-fpq9-mr3gghsax_refsource_CONFIRMWEB
News mentions
6- Amazon Q VS Extension Flaw Leads to Cloud Credential TheftDark Reading · Jun 29, 2026
- Amazon Q Vulnerability Let Attackers Execute Code and Access Sensitive Cloud EnvironmentsCyber Security News · Jun 26, 2026
- Amazon Q Developer Flaw Could Let Malicious Repos Run Code via MCP ConfigsThe Hacker News · Jun 26, 2026
- AI Threat Landscape Digest March-April 2026Check Point Research · May 26, 2026
- Anthropic response to 1-click pwn: Shouldn't have clicked 'ok'The Register Security · May 7, 2026
- 'TrustFall' Convention Exposes Claude Code Execution RiskDark Reading · May 7, 2026