HighVulnerabilityLLM-specific
CVE-2026-117559: DroidMind command injection bypasses shell allowlist via MCP clients
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-117559
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
Summary
DroidMind through 0.4.0 contains a command injection flaw (CVE-2026-117559) that lets MCP clients bypass the shell command allowlist using $(...) or backtick substitution. Attackers, including prompt-injected agents, can pass commands through parameters interpolated into Device.run_shell() or the unvalidated Device.list_directory() to run blocked commands such as reboot on connected Android devices.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Topics
Related items
- Medium'Aokigahara' Stealer Targets 'Developer Keyrings' & AI AssistantsSimilar attack · Dark Reading
- HighGHSA-3w55-933p-8pv5: Strands Agents: Local Privilege Escalation via Symlink Attack in Default Session File StorageSimilar attack · GitHub Advisory Database
- HighGHSA-g5ff-637f-6q2m: LiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials`Similar attack · GitHub Advisory Database
- MediumGHSA-hhww-mrg2-969h: LiteLLM vulnerable to reflected XSS in /sso/debug/callbackSimilar attack · GitHub Advisory Database
- HighCVE-2026-117573: hagent OS command injection through args in arduino and esp32 MCP toolsSimilar attack · NVD/CVE Database