CVE-2026-114107 HKUDS CVE debrief

Who should care

Defenders responsible for securing LLM agents using Vibe-Trading AI tools should assess their exposure and verify the security of their configurations. This includes verifying the exposure of LLM agents to command execution and code injection, assessing the security of LLM agent configurations to prevent SSRF, and applying the fixed version of Vibe-Trading AI package to prevent exploitation. Security teams and vulnerability management teams should also be

Why it matters

CVE-2026-114107 is a vulnerability in Vibe-Trading AI tools that permits command execution, code injection, and SSRF. Defenders should verify exposure, assess configuration security, and apply the fixed version to prevent exploitation.

• Verify exposure of LLM agents to command execution and code injection
• Assess security of LLM agent configurations to prevent SSRF
• Apply fixed version of Vibe-Trading AI package to prevent exploitation
• Verify inventory of affected systems and prioritize remediation

Technical summary

The Vibe-Trading AI tools have multiple vulnerabilities, including shell-injection sinks and codegen vulnerabilities. The tools are part of an auto-discovered tool registry, and their registration is unconditional in default config. These tools permit command execution, code injection, and SSRF. Defenders should assess the security of their configurations and apply the fixed version to prevent exploitation. The vulnerabilities include BashTool shell-injection sink, BackgroundRunTool async shell-injection sink, backtest exec_module() runs top-level statements before the SignalEngine class check, read_url outbound HTTP forwarding without schema/host validation, and Jinja2 codegen with autoescape disabled for .py.

Defensive priority

Defenders should prioritize verifying exposure of LLM agents using Vibe-Trading AI tools and assess the security of their configurations.

Recommended defensive actions

• Verify the exposure of LLM agents using Vibe-Trading AI tools
• Assess the security of LLM agent configurations
• Apply the fixed version (v0.1.7) of the Vibe-Trading AI package
• Review compensating controls for exposed systems while remediation is scheduled and verified
• Check relevant monitoring, detection, and logs for exposed assets that need extra review
• Track exceptions, retest remediated assets, and close the item only after evidence is documented
• Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up

Evidence notes

The source corpus provides details on five findings, including shell-injection sinks and codegen vulnerabilities in Vibe-Trading LLM-callable tools. The CVE record and NVD entry provide additional context.

Sources and references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.