MediumVulnerabilityLLM-specific

CVE-2026-7235: ErlichLiu claude-agent-sdk-master path traversal via outputFile argument

Source: NVD(opens in a new tab)
Identifier: CVE-2026-7235
Published: April 28, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.5%

Summary

CVE-2026-7235 affects ErlichLiu claude-agent-sdk-master up to commit b185aa7ff0d864581257008077b4010fca1747bf. Manipulating the outputFile argument in app/api/agent-output/route.ts leads to path traversal, and the attack may be initiated remotely. The exploit has been publicly disclosed and may be used, and the project was informed through an issue report but has not responded.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 5.3(medium)
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Attack vector: network
Attack complexity: low
Privileges required: none
User interaction: none
EPSS: 0.5%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 9, 2026.
Disclosure date: April 28, 2026

Weaknesses and techniques

Weakness (CWE): CWE-22
Attack pattern (CAPEC): CAPEC-126

Classification

Attack type: Other
Attack sophistication: Trivial
AI component targeted: Agent
Impact: Confidentiality,
Integrity
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-2026-7235

First tracked: April 28, 2026 at 08:09 AM ET, from NVD/CVE Database

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

Classifier confidence: 85% (self-assessed)

Summary

Mitigation

Related items