AI Sec Watch: A Security Intelligence Platform for AI Systems

Luu, T.J.

CriticalVulnerabilityLLM-specific

CVE-2025-54795: Claude Code command parsing flaw bypasses confirmation prompt

Source: NVD(opens in a new tab)
Identifier: CVE-2025-54795
Published: August 4, 2025
Record updated: October 9, 2026

View JSON

Affected: @anthropic-ai/claude-code < 1.0.20
Fixed in: 1.0.20
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 1.0%

Summary

CVE-2025-54795 affects Claude Code versions below 1.0.20. An error in command parsing lets an attacker bypass the Claude Code confirmation prompt and trigger execution of an untrusted command, classified as CWE-78. Exploiting it reliably requires the ability to add untrusted content into a Claude Code context window.

Mitigation

Fixed in version 1.0.20.

Details

Scores and exploitation

CVSS score: 9.8(critical)
Patch available: Yes
EPSS: 1.0%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on October 10, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-78
Attack pattern (CAPEC): CAPEC-88

Affected

Packages: @anthropic-ai/claude-code@< 1.0.20 (fixed: 1.0.20)
Vendors: Anthropic

Classification

Attack type: Other
Attack sophistication: Moderate
AI component targeted: Agent
Impact: Integrity,
Confidentiality,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-54795

First tracked: February 15, 2026 at 08:52 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Topics

AI agents

Summary

Mitigation

Topics

Related items