Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-51871 – Remote Code Execution via LLM Command Injection – Devika v1.0

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-51871 is a critical code injection vulnerability (CWE-94) in Devika, an open-source AI software engineering agent, affecting version 1.0. The flaw resides in the Runner.execute function in src/agents/runner/runner.py, which executes LLM-generated content without validation, sanitization, or sandboxing, allowing an unauthenticated, remote attacker to achieve arbitrary code execution with the privileges of the Devika process. The vulnerability carries a CVSS v3.1 base score of 9.8 (Critical).

Technical details

  • Root cause: Runner.execute (runner.py, around line 199) receives LLM-generated payloads and forwards them to an execution proxy without validating, sanitizing, or sandboxing the content before running it.
  • Trigger conditions: An attacker can influence the content an LLM generates (e.g., by manipulating project context or conversation input across multiple turns) so that malicious instructions are embedded into the code/commands Devika subsequently executes automatically.
  • Attack vector: Network-based; no authentication and no user interaction are required. A publicly disclosed proof-of-concept demonstrates a two-turn conversation flow — the first turn establishes project context, and the second turn injects instructions that the LLM incorporates into generated code, which is then executed directly by Runner.execute.
  • Impact: Full arbitrary code execution in the context of the Devika process, with no confirmation dialogs, whitelisting, or isolation to stop it — resulting in complete loss of confidentiality, integrity, and availability on the host running Devika.

Affected software

  • Devika v1.0 (open-source AI agent framework, stitionai/devika)

Severity

  • CVSS v3.1 Base Score: 9.8 (Critical)
  • Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Mitigation and recommended actions

  • Immediate: At the time of disclosure, no official patched release was confirmed by the vendor. Security teams should monitor the project’s GitHub repository for a fixed release and upgrade as soon as one is published.
  • If no patch is available:
    • Do not expose Devika instances directly to untrusted networks or the public internet; restrict access to trusted, authenticated users only.
    • Run Devika in an isolated, sandboxed environment (e.g., containerized with minimal privileges, no access to sensitive hosts/data, restricted filesystem and network egress).
    • Disable or restrict automatic execution of LLM-generated commands/code; require explicit human review and approval before any generated command is run.
    • Implement command whitelisting and strict input validation around any code/command execution paths.
    • Monitor Devika process activity and logs for unexpected file writes, process spawns, or outbound network connections.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge