{"description":"Trending threats, MITRE ATT\u0026CK coverage, and detection metadata. Fed continuously.","favicon":"https://feed.craftedsignal.io/favicon-32x32.png","feed_url":"https://feed.craftedsignal.io/tags/mcp-server/feed.json","home_page_url":"https://feed.craftedsignal.io/","icon":"https://feed.craftedsignal.io/apple-touch-icon.png","items":[{"_cs_actors":[],"_cs_cpes":[],"_cs_cves":[{"cvss":7.8,"id":"CVE-2026-117558"}],"_cs_exploited":false,"_cs_has_poc":false,"_cs_poc_references":[],"_cs_products":["ai-sdlc plugin MCP server (\u003c= 0.31.2)"],"_cs_severities":["high"],"_cs_tags":["command-injection","vulnerability","mcp-server"],"_cs_type":"advisory","_cs_vendors":[],"content_html":"\u003cp\u003eThe ai-sdlc plugin MCP server through version 0.31.2 contains an OS command injection vulnerability. The repo argument is not validated and is interpolated into gh issue view or gh pr view commands run via execSync(). This allows prompt-injected agents to execute commands as the MCP server user.\u003c/p\u003e\n","date_modified":"2026-10-27T15:49:54Z","date_published":"2026-10-27T15:49:54Z","id":"https://feed.craftedsignal.io/briefs/2026-10-ai-sdlc-cmd-injection/","summary":"The ai-sdlc plugin MCP server through 0.31.2 is vulnerable to OS command injection via the repo argument, allowing execution of commands by supplying shell metacharacters.","title":"ai-sdlc plugin MCP server: OS command injection (CVE-2026-117558)","url":"https://feed.craftedsignal.io/briefs/2026-10-ai-sdlc-cmd-injection/"}],"language":"en","title":"CraftedSignal Threat Feed - Mcp-Server","version":"https://jsonfeed.org/version/1.1"}