Cyber Resilience

CVE-2024-6331

HighPublic PoC

Published: 04 August 2024

Published
04 August 2024
Modified
30 August 2024
KEV Added
—
Patch
—
CVSS Score v3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
EPSS Score 0.0017 37.8th percentile
Risk Priority 15 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2024-6331 is a high-severity Injection (CWE-74) vulnerability in Stitionai Devika. Its CVSS base score is 7.5 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique /etc/passwd and /etc/shadow (T1003.008); ranked at the 37.8th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as Enterprise AI Assistants; in the LLM/Generative AI Risks risk domain; MITRE ATLAS techniques in scope: LLM Prompt Injection (AML.T0051).

EU & UK References

Vulnerability details

stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with `HarmBlockThreshold.BLOCK_NONE` for `HarmCategory.HARM_CATEGORY_HATE_SPEECH` and `HarmCategory.HARM_CATEGORY_HARASSMENT` in `safety_settings` disables content protection. This allows malicious commands to…

more

be executed, such as reading sensitive file contents like `/etc/passwd`.

CWE(s)
CWE-74

AI Security AnalysisAI

AI Category
Enterprise AI Assistants
Risk Domain
LLM/Generative AI Risks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
stitionai/devika is an open-source AI agent/assistant (similar to AI coding engineers like Devin) that integrates Google Gemini LLM, making it an Enterprise AI Assistant vulnerable to prompt injection.

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

T1003.008 /etc/passwd and /etc/shadow Credential Access
Adversaries may attempt to dump the contents of <code>/etc/passwd</code> and <code>/etc/shadow</code> to enable offline password cracking.
attack.mitre.org →
Why these techniques?

The LFI vulnerability via prompt injection allows execution of malicious commands to read sensitive files like /etc/passwd, directly facilitating OS Credential Dumping from /etc/passwd and /etc/shadow.

MITRE ATLAS TechniquesAI

MITRE ATLAS techniques

AML.T0051: LLM Prompt Injection

Affected Assets

stitionai
devika
≥ 2024-05-02

Mitigating Controls

Likely Mitigating Controls AI

Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.

SA-11 Developer Testing and Evaluation
addresses: CWE-74

Developer assessments and testing (including injection-focused techniques) identify improper neutralization of special elements, and the verifiable flaw remediation corrects them pre-deployment.

SI-4 System Monitoring
addresses: CWE-74

Identifies indicators of injection attacks (command, SQL, LDAP, etc.) via anomaly and attack monitoring.

References