Continue CLI versions up to and including 1.5.47 contain a permission bypass vulnerability that allows attackers to execute unauthorized commands by chaining them after allowed Bash prefix rules. This occurs because the application appends attacker-controlled commands after shell command separators such as ;, &&, or |, enabling code execution as the user running the agent.
The Continue CLI applies an incomplete denylist as its only barrier to destructive shell commands when running unattended. In headless mode and auto mode the default policy in extensions/cli/src/permissions/defaultPolicies.ts grants the Bash tool the allow permission, and permissionChecker.ts hard-blocks a command only when the terminal-security evaluator returns a disabled verdict, so isCriticalCommand in packages/terminal-security/src/evaluateTerminalCommandSecurity.ts is the sole control. Its dangerous-path test matches only /, /*, ~, ~/*, /usr, /etc, /bin and /sbin and their prefixes, so a recursive forced removal of /home, /root, /var, /opt or /srv is not disabled. The command line is parsed with shell-quote, which reduces $HOME to an empty token, so rm -rf $HOME also fails the dangerous-path test while the shell re-expands the variable when the command is spawned. find with -delete is rated high risk rather than disabled, and shred, wipefs, truncate and pkexec are not handled. Because the agent autonomously reads content it does not control, including fetched web pages, repository files and issue text, an indirect prompt injection in that content can cause an unattended run to destroy the invoking user's data.
CVE-2026-8770 is a medium severity path traversal vulnerability in continuedev continue versions up to 1.2.22. It affects the lsTool function in the JSON-RPC Server component, allowing local attackers with low privileges to manipulate the dirPath argument to perform path traversal. The vulnerability requires local access and does not involve user interaction. The vendor has not responded to disclosure requests, and no official patch or remediation guidance is currently available. Exploit code is publicly available, but no known exploitation in the wild has been reported.