HighVulnerabilityLLM-specific
CVE-2026-30308: HAI Build Code Generator prompt injection enables arbitrary command execution
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-30308
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.5%
Summary
HAI Build Code Generator offers an Execute safe commands option that auto-runs terminal commands the model classifies as safe, while potentially destructive ones still require user approval. The design is highly susceptible to prompt injection: an attacker can wrap any malicious command in a generic template to make the model classify it as safe, bypassing the approval requirement and enabling arbitrary command execution.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Related items
- HighGHSA-3mgh-93r5-r7jf: CodeWhale: exec_shell parallel-readonly classifier auto-approves fd/rg/git grep exec flags enabling silent RCESimilar attack · GitHub Advisory Database
- HighGHSA-8hp3-xxrg-v9c8: CodeWhale: Automation auto_approve defaults to true, bypassing the task-path hardening fix for silent recurring agent executionSimilar attack · GitHub Advisory Database
- MediumCVE-2026-18883: ServiceNow Email Response AI Agent indirect prompt injection flawSimilar attack · NVD/CVE Database
- InfoAI-Defined Vehicles: Securing the Decisions That Drive Vehicle BehaviorSimilar attack · VicOne Blog
- HighCVE-2026-75612: yt-mcp arbitrary file read through add_attachment file_pathSimilar attack · NVD/CVE Database