Command execution via shell comment parsing mismatch
Published Sep 8, 2026 · Updated Sep 8, 2026
Command injection in Roo Code 3.54.0 and earlier allows attackers to execute denied shell commands through the auto-approve feature. The parseCommand token loop discards shell-quote comment objects after a word-attached hash, while bash treats the hash as literal and executes the hidden separator and command. Exploitation requires always-approve execution and attacker-influenced agent input; commands run with the agent's local privileges.
Summary
What happened
Command injection in Roo Code 3.54.0 and earlier allows attackers to execute denied shell commands through the auto-approve feature. The parseCommand token loop discards shell-quote comment objects after a word-attached hash, while bash treats the hash as literal and executes the hidden separator and command. Exploitation requires always-approve execution and attacker-influenced agent input; commands run with the agent's local privileges.
The record
- CVE
- CVE-2026-82537
- Published
- Sep 8, 2026
- Updated
- Sep 8, 2026
- Vendor
- Roo Code, Inc.
- Product
- Roo Code
- Classifications
- CWE-436, T1059.004
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 8, 2026CVE publishedPublication date reported by the CVE source.
- Sep 8, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <=3.54.0
What conditions does exploitation require?
What is affected?
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Roo Code comment-boundary auto-approve bypass PoCproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo