CVE-2026-91988

critical · 9.2

atomic-agents-stack before 1.1.0 accepts cleartext HTTP schemes in the HTTP MCP server-registry backend factory, allowing network man-in-the-middle attackers to rewrite catalog responses. Attackers can inject arbitrary command and argument values that are spawned as local subprocesses by MCPClientPool to achieve code execution on the agent host.

9.2

CVSS

0.3%

EPSS (exploit prob.)

25th

EPSS percentile

2026-09-15

Published

CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Weaknesses

CWE-319

References

https://github.com/dep0we/atomic-agents-stack/security/advisories/GHSA-xhcr-cqfr-m3hv
https://www.vulncheck.com/advisories/atomic-agents-stack-before-1.1.0-remote-code-execution-via-http-mcp

Query this programmatically:

curl https://evil-db.io/api/v1/cve/CVE-2026-91988