ai-sdlc MCP server command injection via repo argument

high severity · published 2026-10-27

An attacker can run arbitrary OS commands on your machine by putting shell metacharacters in the repo argument of the ai-sdlc MCP server. Because that value is used unvalidated in shell calls, a prompt-injected agent can execute commands as the MCP server user.

CVE: CVE-2026-117558

Source: NVD

Get the fix

FixLane has a reviewed fix procedure for this incident: a read-only check first, then the fix. Ask the Telegram bot, or connect an AI agent to the FixLane MCP server and call get_fix_prompt with incident id 548 and your operating system.