Skip to main content

CVE-2026-114107: Improper Neutralization of Input Used for LLM Prompting in HKUDS Vibe-Trading

0
High
VulnerabilityCVE-2026-114107cvecve-2026-114107
Published: 10/21/2026 (10/21/2026, 00:37:07 UTC)
Source: CVE Database V5
Vendor/Project: HKUDS
Product: Vibe-Trading

Description

HKUDS Vibe-Trading versions from 0.1.0 up to but not including 0.1.7 contain an indirect prompt injection vulnerability. This flaw allows remote attackers to execute arbitrary shell commands as root by embedding malicious instructions in documents or web pages processed by the agent. The vulnerability arises because BashTool and BackgroundRunTool execute model-generated commands using subprocess.run with shell=True without any allow-list or approval mechanism. Additionally, the read_url function can fetch arbitrary URLs, enabling server-side request forgery. The vulnerability has a high severity rating with a CVSS score of 8.7.

CVSS v4.0

Score 8.7high

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
Passive
Vuln. Confidentiality
High
Vuln. Integrity
High
Vuln. Availability
High
Subsq. Confidentiality
None
Subsq. Integrity
None
Subsq. Availability
None
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Affected software

HKUDS

Vibe-Trading

Affected versions
>=0.1.0 <0.1.7
GitHub Actionsmore threats →ai
hkuds/Vibe-Trading
pkg:github/hkuds/Vibe-Trading

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 10/21/2026, 01:03:57 UTC

Technical Analysis

The vulnerability in HKUDS Vibe-Trading (>=0.1.0 <0.1.7) is an indirect prompt injection that permits remote attackers to execute shell commands as root. This occurs because the tools BashTool and BackgroundRunTool pass commands emitted by the language model directly to subprocess.run with shell=True, lacking any filtering or approval steps. The read_url function further enables server-side request forgery by fetching arbitrary URLs. This combination allows attackers to plant instructions in documents or web pages processed by the agent, leading to command execution and SSRF.

Potential Impact

Successful exploitation allows remote attackers to execute arbitrary shell commands with root privileges on the affected system. This can lead to full system compromise, unauthorized data access, and further network pivoting. The server-side request forgery capability also enables attackers to make arbitrary HTTP requests from the vulnerable server, potentially accessing internal resources.

Mitigation Recommendations

No patch or official fix information is provided in the available data. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, avoid processing untrusted documents or web pages with the affected versions of HKUDS Vibe-Trading. Implement network-level restrictions to limit outbound requests from the server to mitigate SSRF risks.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
VulnCheck
Date Reserved
2026-10-20T21:47:43.313Z
Cvss Version
4.0
State
PUBLISHED

Threat ID: 6ad80c0a2cdf04f6568caa5e

Added to database: 10/21/2026, 00:49:14 UTC

Last enriched: 10/21/2026, 01:03:57 UTC

Last updated: 10/21/2026, 01:08:29 UTC

Views: 4

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses