HighVulnerabilityLLM-specific

CVE-2026-75062: Google langfun eval injection in default lf.query Python protocol

Source: NVD(opens in a new tab)
Identifier: CVE-2026-75062
Published: August 26, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.4%

Summary

CVE-2026-75062 is an Eval Injection flaw (CWE category: Improper Neutralization of Directives in Dynamically Evaluated Code) in the default lf.query Python protocol of Google langfun, affecting versions prior to 0.1.2. Remote unauthenticated attackers can use crafted prompt inputs to make the model generate Python expressions, which are evaluated without a sandbox, letting them execute arbitrary Python code in the context of the host application.

Mitigation

Fixed in 0.1.2 (langfun versions prior to 0.1.2 are affected).

Details

Scores and exploitation

EPSS: 0.4%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.
Disclosure date: August 26, 2026

Weaknesses and techniques

Weakness (CWE): CWE-95
CWE-1188
Attack pattern (CAPEC): CAPEC-242
AI threat technique (MITRE ATLAS): AML.T0054

Affected

Vendors: Google

Classification

Attack type: Jailbreak,
Other
Attack sophistication: Trivial
AI component targeted: Framework
Impact: Confidentiality,
Integrity,
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-2026-75062

First tracked: August 26, 2026 at 02:07 PM ET, from NVD/CVE Database

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

Classifier confidence: 90% (self-assessed)

Summary

Mitigation

Related items