Security Digest · Vulnerability record

CVE-2024-5826: vanna vulnerable to remote code execution caused by prompt injection

In the latest version of vanna-ai/vanna, the vanna.ask function is vulnerable to remote code execution due to prompt injection.

CVSS 9.8 Critical EPSS 0.9% · p59

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

  • Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
  • EPSS 0.9%, percentile 59: FIRST’s model estimates a 0.9% chance of exploitation activity in the next 30 days, higher than 59% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
  • Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
  • Only applies if your dependency tree includes vanna (PyPI) <= 0.6.2, no fixed version listed. Check your lockfile, including transitive dependencies.

What it is

In the latest version of vanna-ai/vanna, the vanna.ask function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the exec function in src/vanna/base/base.py. This vulnerability can be exploited by an attacker to achieve remote code execution on the app backend server, potentially gaining full control of the server.

From the GitHub advisory

In the latest version of vanna-ai/vanna, the vanna.ask function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the exec function in src/vanna/base/base.py. This vulnerability can be exploited by an attacker to achieve remote code execution on the app backend server, potentially gaining full control of the server.

Weakness type: CWE-94.

Product: vanna (PyPI) · Assigned by: @huntr_ai · Published: 2024-06-27

Affected and fixed versions

EcosystemPackageVulnerableFirst fixed
PyPIvanna<= 0.6.2none listed
VendorProductAffected versions (per CVE record)
vanna-aivanna-ai/vannaunspecified <= latest

Severity scores

Scored byCVSSScoreVector
@huntr_ai3.09.8 CriticalCVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GitHub3.19.8 CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
  • Attack vector: network (remotely reachable)
  • Attack complexity: low
  • Privileges required: none (no login)
  • User interaction: none
  • Scope: unchanged

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

  • CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
  • CISA SSVC assessment: exploitation poc, automatable no, technical impact total.
  • FIRST EPSS (model of 2026-10-21): 0.88% probability of exploitation activity in the next 30 days; percentile 59.

Timeline

  • — CVE record published by @huntr_ai
  • — GitHub-reviewed advisory GHSA-rrqq-fv6m-692m published (critical)
  • — CVE record last updated

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vulnerability records

  1. GitHub Advisory GHSA-rrqq-fv6m-692m github.com
  2. CVE.org record CVE-2024-5826 cve.org
  3. NVD entry CVE-2024-5826 nvd.nist.gov

Other references from the CVE record and advisory

  1. huntr.com huntr.com

Critical PyPI advisories · Today’s Security Digest