Description
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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| dep0we | atomic-agents-stack | < 1.1.0 | 1.1.0 |
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | atomic-agents-stack | < 1.1.0 | 1.1.0 | GHSA-xhcr-cqfr-m3hv |
References
- GitHub Security Advisory (GHSA-xhcr-cqfr-m3hv) vendor-advisory
- VulnCheck Advisory: atomic-agents-stack before 1.1.0 Remote Code Execution via HTTP MCP third-party-advisory