https://patchthecve.com/CVEs with upgrade or downgrade fix stepshttps://patchthecve.com/cve/CVE-2026-110206.htmlhttps://patchthecve.com/cve/CVE-2026-110206.htmlFri, 16 Oct 2026 23:16:59 +0000HIGH 8.8: 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 $(echo touch /tmp/x)https://patchthecve.com/cve/CVE-2026-110205.htmlhttps://patchthecve.com/cve/CVE-2026-110205.htmlMon, 26 Oct 2026 20:17:48 +0000HIGH 8.8: Roo Code through 3.54.0 contains a command approval bypass vulnerability in parseCommandLine() that discards command substitutions placed next to * or ? glob characters. Attackers using indirect prompt injection can craft commands like echo *$(...) that match allowlisted prefixes, executing denied chttps://patchthecve.com/cve/CVE-2026-110204.htmlhttps://patchthecve.com/cve/CVE-2026-110204.htmlThu, 15 Oct 2026 19:05:21 +0000HIGH 8.8: 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 allowlistedhttps://patchthecve.com/cve/CVE-2026-110203.htmlhttps://patchthecve.com/cve/CVE-2026-110203.htmlThu, 15 Oct 2026 19:06:19 +0000HIGH 8.8: Roo Code through 3.54.0 contains a command approval bypass vulnerability that allows attackers to auto-approve denied shell commands by abusing quote-masking regex in parseCommandLine(). Attackers can use indirect prompt injection with escaped or single-quoted double quotes to hide command separatorhttps://patchthecve.com/cve/CVE-2026-110202.htmlhttps://patchthecve.com/cve/CVE-2026-110202.htmlThu, 15 Oct 2026 19:09:07 +0000HIGH 8.8: Roo Code through 3.54.0 contains a command approval bypass vulnerability in getCommandDecision() that allows attackers to auto-approve denied shell commands by prefixing them with a bare >& redirect. Attackers using indirect prompt injection can make the allowlist match a redirect target like echo w