CVE-2026-76072: Incomplete List of Disallowed Inputs in continuedev continue
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.
AI Analysis
Technical Summary
The Continue CLI applies an incomplete denylist as its sole barrier against destructive shell commands during unattended runs. In headless and auto modes, the Bash tool is allowed by default, and commands are only blocked if the terminal-security evaluator returns a disabled verdict. The dangerous-path test only matches certain root-level directories and their prefixes, missing critical directories like /home, /root, /var, /opt, and /srv, allowing recursive forced removal commands targeting these paths to proceed unchecked. The command line parsing reduces $HOME to an empty token, causing commands like 'rm -rf $HOME' to bypass the dangerous-path test while the shell re-expands the variable at execution. Furthermore, commands such as find with -delete are rated high risk but not disabled, and shred, wipefs, truncate, and pkexec are not handled at all. Since the agent autonomously reads and executes content from external sources including web pages, repository files, and issue text, an indirect prompt injection vulnerability exists that could lead to unattended destructive command execution, resulting in data loss.
Potential Impact
This vulnerability allows an attacker to indirectly inject destructive shell commands that bypass the Continue CLI's incomplete denylist protections. As a result, unattended runs of the CLI can execute recursive forced removals of critical user directories and other destructive operations, potentially causing significant data loss for the invoking user. The vulnerability affects the integrity and availability of user data on systems running vulnerable versions of the Continue CLI.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, users should avoid running unattended Continue CLI operations in headless or auto mode, especially when processing untrusted external content. Restricting the CLI's access to critical system directories and monitoring for suspicious command executions may help reduce risk. Review and update denylist policies to include all critical system paths and handle all known destructive commands appropriately.
CVE-2026-76072: Incomplete List of Disallowed Inputs in continuedev continue
Description
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.
CVSS v4.0
Score 8.3high
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
The Continue CLI applies an incomplete denylist as its sole barrier against destructive shell commands during unattended runs. In headless and auto modes, the Bash tool is allowed by default, and commands are only blocked if the terminal-security evaluator returns a disabled verdict. The dangerous-path test only matches certain root-level directories and their prefixes, missing critical directories like /home, /root, /var, /opt, and /srv, allowing recursive forced removal commands targeting these paths to proceed unchecked. The command line parsing reduces $HOME to an empty token, causing commands like 'rm -rf $HOME' to bypass the dangerous-path test while the shell re-expands the variable at execution. Furthermore, commands such as find with -delete are rated high risk but not disabled, and shred, wipefs, truncate, and pkexec are not handled at all. Since the agent autonomously reads and executes content from external sources including web pages, repository files, and issue text, an indirect prompt injection vulnerability exists that could lead to unattended destructive command execution, resulting in data loss.
Potential Impact
This vulnerability allows an attacker to indirectly inject destructive shell commands that bypass the Continue CLI's incomplete denylist protections. As a result, unattended runs of the CLI can execute recursive forced removals of critical user directories and other destructive operations, potentially causing significant data loss for the invoking user. The vulnerability affects the integrity and availability of user data on systems running vulnerable versions of the Continue CLI.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, users should avoid running unattended Continue CLI operations in headless or auto mode, especially when processing untrusted external content. Restricting the CLI's access to critical system directories and monitoring for suspicious command executions may help reduce risk. Review and update denylist policies to include all critical system paths and handle all known destructive commands appropriately.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-08-18T21:04:48.504Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a8c8878acd9273b49ee3f3a
Added to database: 08/24/2026, 18:07:52 UTC
Last enriched: 08/24/2026, 18:22:16 UTC
Last updated: 08/24/2026, 18:52:46 UTC
Views: 5
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.