Cyber Resilience

CVE-2024-6331

Stitionai Devika ≥ 2024-05-02

Public PoC
Published
04 August 2024
Modified
30 August 2024
CVSS Score v3.1 7.5
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
EPSS Score 0.0050 40th percentile
Risk Priority 58 floored blend · peak EPSS

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 Exploit Public-Facing Application (T1190); ranked at the 40th 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.

The strongest mitigations our analysis identified map to SI-10 (Information Input Validation) — see the control section below for these in your framework.

OWASP Top 10 for Web (2025)

A05:2025 Injection

EU & UK References

Vulnerability Data

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
AI-specific weaknesses CR
CWE-1427CWE-1426CWE-1434
  • CWE-1427 — Prompt injection (untrusted input to LLM) + unsafe model output to file sink + disabled safety filters.
Mapped by Cyber Resilience · not in NVD. Poisoning and extraction cases are routed to MITRE ATLAS instead of a synthetic CWE.
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 Techniques

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
attack.mitre.org →
T1221 Template Injection Stealth
Adversaries may create or modify references in user document templates to conceal malicious code or force authentication attempts.
attack.mitre.org →
T1659 Content Injection Initial Access
Adversaries may gain access and continuously communicate with victims by injecting malicious content into systems through online network traffic.
attack.mitre.org →
T1674 Input Injection Execution
Adversaries may simulate keystrokes on a victim’s computer by various means to perform any type of action on behalf of the user, such as launching the command interpreter using keyboard shortcuts, typing an inline script to be executed,…
attack.mitre.org →
T1059 Command and Scripting Interpreter Execution
Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.
attack.mitre.org →
T1059.001 PowerShell Execution
Adversaries may abuse PowerShell commands and scripts for execution.
attack.mitre.org →
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2026-47644Shared CWE-74
CVE-2026-41109Shared CWE-74
CVE-2024-5184Shared CWE-74
CVE-2026-33833Shared CWE-74
CVE-2025-32711Shared CWE-74
CVE-2026-26164Shared CWE-74
CVE-2023-23749Shared CWE-74
CVE-2023-48835Shared CWE-74
CVE-2023-51939Shared CWE-74
CVE-2023-33242Shared CWE-74

Affected Assets

stitionai
devika
≥ 2024-05-02

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

—

Detect
Catch it (NIST detect / respond)

—

Harden
Shrink the surface (DISA STIG)

—

Validate
Prove the fix (OWASP ASVS)
  • V1.2.1
  • V1.2.3
  • V1.2.5
  • V1.2.8

Mitigating Controls (NIST 800-53 r5) AI

SI-10 Information Input Validation good match

SI-10 directly requires validation of information inputs to reject malformed or special-element content before it reaches downstream parsers.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 mostly match
prevents

Secure SDLC practices directly require input validation and output encoding that prevent injection flaws.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

A.8.29 Security testing in development and acceptance mostly match
finds

Security testing in development catches injection vulnerabilities before release.

A.8.15 Logging partial match
finds

Logging supports detection of injection attempts but does not prevent the weakness.

A.8.16 Monitoring activities partial match
finds

Monitoring activities can identify active injection attacks after they occur.

A.8.25 Secure development life cycle partial match
prevents

Secure development life cycle mandates input validation and output encoding that directly prevent injection flaws.

A.8.26 Application security requirements partial match
prevents

Application security requirements explicitly call for controls against injection attacks in software design.

A.8.27 Secure system architecture and engineering principles partial match
prevents

Secure architecture principles reduce injection surfaces but do not prescribe specific neutralization techniques.

References