CVE-2026-63108: Incomplete List of Disallowed Inputs in RooCodeInc Roo-Code
Roo Code through 3.54.0 contains a command injection vulnerability in the auto-approve execute feature that allows attackers to bypass allowlist/denylist enforcement by nesting command substitutions inside parameter expansion defaults. The command parser in parse-command.ts replaces parameter expansions with opaque placeholders before extracting command substitutions, causing the containsDangerousSubstitution guard to miss nested payloads, which are then auto-approved based on the outer allowlisted command prefix and executed by the shell via execa, enabling arbitrary command execution.
AI Analysis
Technical Summary
CVE-2026-63108 affects Roo-Code through version 3.54.0. The vulnerability arises from the command parser in parse-command.ts, which replaces parameter expansions with opaque placeholders before extracting command substitutions. This process causes the containsDangerousSubstitution guard to fail to detect nested command substitutions embedded inside parameter expansion defaults. As a result, attackers can craft nested payloads that bypass the allowlist/denylist enforcement in the auto-approve execute feature. These nested payloads are then auto-approved based on the outer allowlisted command prefix and executed by the shell via execa, leading to arbitrary command execution.
Potential Impact
Successful exploitation allows unauthenticated attackers to execute arbitrary commands on the system where Roo-Code is running. This can lead to full system compromise, data theft, or disruption of service. The vulnerability is remotely exploitable without privileges but requires user interaction (UI:P). The overall impact on confidentiality, integrity, and availability is high.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. No official fix or temporary workaround has been provided at this time. Until a patch is available, avoid using the auto-approve execute feature or restrict its usage to trusted inputs only.
CVE-2026-63108: Incomplete List of Disallowed Inputs in RooCodeInc Roo-Code
Description
Roo Code through 3.54.0 contains a command injection vulnerability in the auto-approve execute feature that allows attackers to bypass allowlist/denylist enforcement by nesting command substitutions inside parameter expansion defaults. The command parser in parse-command.ts replaces parameter expansions with opaque placeholders before extracting command substitutions, causing the containsDangerousSubstitution guard to miss nested payloads, which are then auto-approved based on the outer allowlisted command prefix and executed by the shell via execa, enabling arbitrary command execution.
CVSS v4.0
Score 7.7high
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-63108 affects Roo-Code through version 3.54.0. The vulnerability arises from the command parser in parse-command.ts, which replaces parameter expansions with opaque placeholders before extracting command substitutions. This process causes the containsDangerousSubstitution guard to fail to detect nested command substitutions embedded inside parameter expansion defaults. As a result, attackers can craft nested payloads that bypass the allowlist/denylist enforcement in the auto-approve execute feature. These nested payloads are then auto-approved based on the outer allowlisted command prefix and executed by the shell via execa, leading to arbitrary command execution.
Potential Impact
Successful exploitation allows unauthenticated attackers to execute arbitrary commands on the system where Roo-Code is running. This can lead to full system compromise, data theft, or disruption of service. The vulnerability is remotely exploitable without privileges but requires user interaction (UI:P). The overall impact on confidentiality, integrity, and availability is high.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. No official fix or temporary workaround has been provided at this time. Until a patch is available, avoid using the auto-approve execute feature or restrict its usage to trusted inputs only.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-07-15T15:45:44.602Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a5e6c132a4a8d59898880f8
Added to database: 07/20/2026, 18:42:27 UTC
Last enriched: 07/20/2026, 18:56:40 UTC
Last updated: 07/21/2026, 06:00:14 UTC
Views: 16
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.