Skip to content
HighVulnerabilityLLM-specific

CVE-2026-30308: HAI Build Code Generator prompt injection enables arbitrary command execution

Identifier
CVE-2026-30308
Published
Record updated
View JSON
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.