CVE-2026-75062: Eval Injection in google/langfun via default lf.query protocol
- Is it exploited?
Not on CISA's list. CISA has not added it to the Known Exploited Vulnerabilities catalog as of . If CISA adds it, this page shows it as known exploited.
- How likely is exploitation in the next 30 days?
- 0.4%
EPSS score, percentile 28.6 of all scored records. A probability estimated by FIRST, not a report of exploitation.
CISA's SSVC assessment in the CVE record lists exploitation as poc.
- How severe?
- 9.2 Critical
CVSS v4.0 base score, given by the CNA
- What should I do?
CISA has set no required action, because the vulnerability is not in KEV.
The CVE record links no vendor advisory, patch or mitigation.
- Which versions are affected?
Affected
- from 0.0.1 to before 0.1.2
Source: CISA KEV 2026.10.29, as of ; FIRST EPSS, as of ; CVE List, as of . About the data.
What to do
Advisories and patches
The CVE record links no vendor advisory, patch or mitigation.
This summary is based on the CVE record as of . Check the vendor's advisory before you act: affected versions and fixes can change.
Affected products and versions
As listed in the CVE record.
| Status | Versions |
|---|---|
| Affected | from 0.0.1 to before 0.1.2 |
Versions not listed are: unaffected.
Source: CVE List, as of . About the data.
About this vulnerability
Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection') in the default lf.query Python protocol in Google langfun versions prior to 0.1.2 allows remote unauthenticated attackers to execute arbitrary Python code in the context of the host application via crafted prompt inputs that cause the model to generate executable Python expressions evaluated without a sandbox.
Summary: CVE record, as of .
- CISA has not added CVE-2026-75062 to its Known Exploited Vulnerabilities (KEV) catalog, as of 29 Oct 2026.
- The CVE record was published on 26 Aug 2026.
- The CVE record carries a CVSS v4.0 base score of 9.2 (Critical), given by its CNA.
- FIRST's EPSS model puts the probability of exploitation in the next 30 days at 0.4% (percentile 28.6), as of 29 Oct 2026. EPSS is a statistical estimate, not a report of exploitation.
- CISA's SSVC assessment in the CVE record: exploitation poc, automatable no, technical impact total.
Source: CISA KEV 2026.10.29, as of ; CVE List, as of ; FIRST EPSS, as of . About the data.
Description
Eval Injection in google/langfun via default lf.query protocol
Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection') in the default lf.query Python protocol in Google langfun versions prior to 0.1.2 allows remote unauthenticated attackers to execute arbitrary Python code in the context of the host application via crafted prompt inputs that cause the model to generate executable Python expressions evaluated without a sandbox.
Source: CVE List, as of . About the data.
Weakness
CWE-95, CWE-1188, 1 CAPEC
- CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')
- CWE-1188: Insecure Default Initialization of Resource
Attack patterns (CAPEC)
- CAPEC-242: Code Injection
CWE and CAPEC are maintained by MITRE; the entries are those named in the CVE record.
Timeline
| Date | Event |
|---|---|
| CVE record published | |
| CVE record last updated |
References
2
Known exploited Google vulnerabilities
- CVE-2026-111497: Google Brotli Unchecked Return Value Vulnerability
- CVE-2026-58704: Google Pixel Improper Authorization Vulnerability
- CVE-2026-87491: Google Chromium V8 Out of Bounds Write Vulnerability
- CVE-2026-85046: Google Chromium V8 Type Confusion Vulnerability
- CVE-2026-11645: Google Chromium V8 Out-of-Bounds Read and Write Vulnerability