HighVulnerabilityLLM-specific

CVE-2024-6331: stitionai/devika local file read through prompt injection

Source: NVD(opens in a new tab)
Identifier: CVE-2024-6331
Published: August 3, 2024
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-2024-6331 affects the stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f. The integration of Google Gemini 1.0 Pro sets HarmBlockThreshold.BLOCK_NONE for HARM_CATEGORY_HATE_SPEECH and HARM_CATEGORY_HARASSMENT in safety_settings, which disables content protection. This allows prompt injection to read local files such as /etc/passwd.

Mitigation

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

Details

Scores and exploitation

CVSS score: 7.5(high)
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 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-74
CWE-74
AI threat technique (MITRE ATLAS): AML.T0051

Affected

Vendors: Google

Classification

Attack type: Prompt injection
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-2024-6331

First tracked: February 15, 2026 at 08:52 PM ET, from NVD/CVE Database

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

Classifier confidence: 95% (self-assessed)

Summary

Mitigation

Related items