← Back to search

CVE-2026-110205

8.8 HIGHpublic exploit available

Published 2026-10-13 · Updated 2026-10-15

AI risk analysis

Summary
Roo Code allows attackers to bypass command approval by crafting malicious commands that use glob characters like * or ? next to command substitutions, enabling execution of denied commands when auto-approval is enabled.
Exploitability
Moderately difficult to exploit as it requires indirect prompt injection to craft commands like echo *$(...) that match allowlisted prefixes, but the vulnerability is highly impactful once achieved.
Blast radius
High impact across all systems using Roo Code with auto-approval enabled, potentially allowing full command execution and system compromise.
Detection
No reliable host or network indicator is derivable from the published description.
Prioritized remediation
Upgrade to roocode version 3.54.1 or later to fix the command approval bypass vulnerability.
command-injectionbypassclirce

Analysis generated locally by garnet-coder (no data left the box). AI-assisted — verify against primary sources before acting.

NVD description

Roo Code through 3.54.0 contains a command approval bypass vulnerability in parseCommandLine() that discards command substitutions placed next to * or ? glob characters. Attackers using indirect prompt injection can craft commands like echo *$(...) that match allowlisted prefixes, executing denied commands without user approval when auto-approval is enabled.

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Weaknesses

CWE-184

Vendors

roocode

Products

roo code

Public exploit & PoC references

All references

Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.

Related CVEs

Related by shared AI tags and CWE weakness class. Browse the full archive.