← Back to search

CVE-2026-110206

8.8 HIGHpublic exploit available

Published 2026-10-13 · Updated 2026-10-16

AI risk analysis

Summary
Roo Code allows attackers to bypass command approval by injecting command substitutions that execute arbitrary shell commands without user approval. This vulnerability enables remote code execution through indirect prompt injection.
Exploitability
Exploitation is relatively straightforward requiring only a single malicious command injection like $(echo touch /tmp/x) that passes the echo allowlist check, with no additional prerequisites needed.
Blast radius
The impact could be significant across all systems running Roo Code 3.54.0 or earlier, potentially allowing full system compromise through arbitrary command execution.
Detection
No reliable host or network indicator is derivable from the published description.
Prioritized remediation
Upgrade to Roo Code 3.55.0 or later to address this command approval bypass vulnerability.
rcecommand-injectionclishell

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 allows attackers to auto-approve arbitrary shell commands by placing a command substitution in command position. Attackers using indirect prompt injection can submit commands like $(echo touch /tmp/x) that pass the echo allowlist check, causing the shell to execute the output without user approval.

CVSS vector

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

Weaknesses

CWE-436

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.