Skip to main content
Public proof of conceptFix available

CVE-2024-21513

A public proof of concept exists; no exploitation attested.

  • Published2024-07-15
  • Fixed in0.0.21
  • WeaknessCWE-94

Am I affected?

With a domain, we read the version its public headers and pages expose. A distribution build can carry the fix under an older number.

Description

Versions of the package langchain-experimental from 0.0.15 and before 0.0.21 are vulnerable to Arbitrary Code Execution when retrieving values from the database, the code will attempt to call 'eval' on all values. An attacker can exploit this vulnerability and execute arbitrary python code if they can control the input prompt and the server is configured with VectorSQLDatabaseChain. **Notes:** Impact on the Confidentiality, Integrity and Availability of the vulnerable component: Confidentiality: Code execution happens within the impacted component, in this case langchain-experimental, so all resources are necessarily accessible. Integrity: There is nothing protected by the impacted component inherently. Although anything returned from the component counts as 'information' for which the trustworthiness can be compromised. Availability: The loss of availability isn't caused by the attack itself, but it happens as a result during the attacker's post-exploitation steps. Impact on the Confidentiality, Integrity and Availability of the subsequent system: As a legitimate low-privileged user of the package (PR:L) the attacker does not have more access to data owned by the package as a result of this vulnerability than they did with normal usage (e.g. can query the DB). The unintended action that one can perform by breaking out of the app environment and exfiltrating files, making remote connections etc. happens during the post exploitation phase in the subsequent system - in this case, the OS. AT:P: An attacker needs to be able to influence the input prompt, whilst the server is configured with the VectorSQLDatabaseChain plugin.

Timeline

dates in UTC
  1. 2024-07-1505:15CVE publishedNVD
  2. 2026-10-2319:23First public proof of conceptPoC-in-GitHub

Observed activity

isMalicious corpus · updated 2026-10-23 18:48 UTC
Indicators tagged with this CVE, per day0 indicators over 7 days
Block these indicators
  • Firewall list (EDL, text): https://api.ismalicious.com/edl/cve/CVE-2024-21513?format=txt
  • CSV export: https://api.ismalicious.com/edl/cve/CVE-2024-21513?format=csv
  • TAXII collection of exploited CVEs
  • The EDL and CSV take an API key on the Pro plan.

Versions per branch

CISA-ADP · NVD
Langchain langchain experimental
BranchAffectedFixed in
0.0≥ 0.0.15, < 0.0.210.0.21
Langchain langchain-experimental
BranchAffectedFixed in
0.0≥ 0.0.15, < 0.0.210.0.21

as publishedRanges as NVD and OSV publish them; a distribution’s build can be fixed under an older number.

Fix

  1. Update Langchain langchain experimental to 0.0.21

Advisories and patches

Detection

read 2026-10-23 19:24 UTC
Nuclei template
none so far
ProjectDiscovery
Exploit-DB
no entry
Exploit-DB
Proof-of-concept repositories
2 repositories, unverifiedSavageSanta11/Reproduce-CVE-2024-21513nskath/CVE-2024-21513
PoC-in-GitHub

Sources

  • CISA-ADPSSVC decisionnone2024-07-15
  • OpenCVESSVC decisionnone—
  • CNACVSS 3.18.5read 2026-10-23
  • NVDCVSS 3.18.5read 2026-10-23
  • CISA-ADPweakness (CWE)CWE-942024-07-15
  • CNAweakness (CWE)CWE-94read 2026-10-23
  • FIRST EPSSEPSS score1.9 %2026-10-22
  • PoC-in-GitHubproof of concept2read 2026-10-23

Technical details

CVSS v3 Vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:H
Published
2024-07-15
Last Modified
2026-06-17
NVD status
Modified

Frequently asked questions

What is CVE-2024-21513?

Versions of the package langchain-experimental from 0.0.15 and before 0.0.21 are vulnerable to Arbitrary Code Execution when retrieving values from the database, the code will attempt to call 'eval' on all values. An attacker can exploit this vulnerability and execute arbitrary python code if they can control the input prompt and the server is configured with VectorSQLDatabaseChain. **Notes:** Impact on the Confidentiality, Integrity and Availability of the vulnerable component: Confidentiality: Code execution happens within the impacted component, in this case langchain-experimental, so all resources are necessarily accessible. Integrity: There is nothing protected by the impacted component inherently. Although anything returned from the component counts as 'information' for which the trustworthiness can be compromised. Availability: The loss of availability isn't caused by the attack itself, but it happens as a result during the attacker's post-exploitation steps. Impact on the Confidentiality, Integrity and Availability of the subsequent system: As a legitimate low-privileged user of the package (PR:L) the attacker does not have more access to data owned by the package as a result of this vulnerability than they did with normal usage (e.g. can query the DB). The unintended action that one can perform by breaking out of the app environment and exfiltrating files, making remote connections etc. happens during the post exploitation phase in the subsequent system - in this case, the OS. AT:P: An attacker needs to be able to influence the input prompt, whilst the server is configured with the VectorSQLDatabaseChain plugin.

Is CVE-2024-21513 actively exploited?

Active exploitation of CVE-2024-21513 has not been confirmed. Its EPSS score was 1.9% on 2026-10-22, the estimated probability of exploitation in the next 30 days.

What is the CVSS score for CVE-2024-21513?

CVE-2024-21513 has a CVSS v3 base score of 8.5 (HIGH severity), with vector string CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:H.

Hear about the next vulnerability in your software

Surveillance reads the versions in your stack — a domain, a lockfile or a list — checks each CVE against the ranges its sources publish, and alerts you when one you run is exploited or enters CISA KEV. A version it cannot read stays « version not verified ».

Get alerts for this productCISA KEV additions, October 2026Search CVEs

No credit card required · No monthly cap on website lookups · 250 API requests/month

Go further

Related vulnerabilities

Same product first, then the same vendor advisory and the same publication week.

Back to CVE Database