Skip to content
HighVulnerabilityLLM-specific

CVE-2026-30310: Sixth terminal command auto-execution bypassed via prompt injection

Identifier
CVE-2026-30310
Published
Record updated
View JSON
Known exploitation
Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS
0.5%

Summary

CVE-2026-30310 affects Sixth's automatic terminal command execution, which offers an "Execute safe commands" option and an "Execute all commands" option. Under the safe-commands setting, the model decides whether a command is safe and runs it without asking, while commands it judges potentially destructive still require user approval. An attacker can wrap a 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.