Command execution via rg approval bypass
Published Sep 10, 2025 · Updated Sep 11, 2025
Command injection in Claude Code before 1.0.105 allows attackers to execute untrusted commands by bypassing the approval prompt. An error in the rg command parser lets attacker-influenced content evade the confirmation check; Anthropic has not disclosed the specific parsing error or token sequence. Exploitation requires untrusted content to enter a Claude Code context window, after which commands run with the privileges of the Claude Code process.
Summary
What happened
Command injection in Claude Code before 1.0.105 allows attackers to execute untrusted commands by bypassing the approval prompt. An error in the rg command parser lets attacker-influenced content evade the confirmation check; Anthropic has not disclosed the specific parsing error or token sequence. Exploitation requires untrusted content to enter a Claude Code context window, after which commands run with the privileges of the Claude Code process.
The record
- CVE
- CVE-2025-58764
- Published
- Sep 10, 2025
- Updated
- Sep 11, 2025
- Vendor
- Anthropic
- Product
- Claude Code
- Classifications
- CWE-94, T1059
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 10, 2025CVE publishedPublication date reported by the CVE source.
- Sep 11, 2025Record 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=< 1.0.105
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
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
No public exploit references are available in this record.
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