Findings

CVE-2026-110204

Roo Code through 3.54.0 contains a command approval bypass vulnerability that allows attackers to run denied shell commands because parseCommandLine() treats ${ comman…

Published Oct 13, 2026 · updated Oct 15, 2026 · roocode roo code

Roo Code through 3.54.0 contains a command approval bypass vulnerability that allows attackers to run denied shell commands because parseCommandLine() treats ${ command; } substitutions as parameter expansions. Attackers using indirect prompt injection can embed denied commands inside an allowlisted command like echo to execute them without user approval on bash 5.3+ or ksh93.

Code

The project this record applies to. Exploit listings stay in References.

Timeline

Detection, updates, and resolution for this record.

  1. Oct 13, 2026 · NIST NVD

    Detected

    Roo Code through 3.54.0 contains a command approval bypass vulnerability that allows attackers to run denied shell commands because parseCommandLine() treats ${ command; } substitutions as parameter expansions. Attackers using indirect prompt injection can embed denied commands inside an allowlisted command like echo to execute them without user approval on bash 5.3+ or ksh93.

  2. Oct 15, 2026 · NIST NVD

    Updated

    Roo Code through 3.54.0 contains a command approval bypass vulnerability that allows attackers to run denied shell commands because parseCommandLine() treats ${ command; } substitutions as parameter expansions. Attackers using indirect prompt injection can embed denied commands inside an allowlisted command like echo to execute them without user approval on bash 5.3+ or ksh93.

Affected

  • cpe roocode/roo codeversion unspecified

Sources

  • CVE.orgVulnerability recordCVE-2026-110204

    Official CVE identifier

    cve.org
  • NIST NVDVulnerability recordCVE-2026-110204

    Roo Code through 3.54.0 contains a command approval bypass vulnerability that allows attackers to run denied shell commands because parseCommandLine() treats ${ command; } substitutions as parameter expansions. Attackers using indirect prompt injection can embed denied commands i

    nvd.nist.gov

References

CVE-2026-110204 · ZeroDay Findings