UTC
High

Claude Code rg vulnerability does not protect against approval prompt bypass

CVE-2025-58764 · GHSA-qxfv-fcpc-w36x · published 2025-09-10

Severity
High
CVSS score
8.7
Chance of exploitation (EPSS)
0.55%
Fixed in
1.0.105
  • Exploitation No known exploitation
  • Automatable Yes
  • Technical impact Total
  • CISA SSVC
What it is

Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window.

What to do

Upgrade @anthropic-ai/claude-code to 1.0.105 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

Affected
PackageRegistryAffectedFixed in
@anthropic-ai/claude-codenpm< 1.0.1051.0.105

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].