atomic-agents-stack
Affected
- introduced
0, fixed1.1.0(ecosystem)
Fixed versions
1.1.0
Fix
- Fixed version
1.1.0pip install --upgrade atomic-agents-stack==1.1.0
Advisory
Also known as: CVE-2026-91988
atomic-agents-stack: HTTP MCP catalog accepts cleartext http and spawns catalog-supplied commands (MITM to RCE)
The HTTP MCP server-registry backend factory (atomic_agents/mcp_registry/http.py, make_http_mcp_server_registry_backend_from_url) accepts both http and https schemes. Catalog entries carry command/args that are type-validated but content-unrestricted, and are later spawned as local stdio subprocesses by MCPClientPool. Over a cleartext http:// catalog URL, a network man-in-the-middle can rewrite the catalog response to inject an arbitrary command/args and obtain code execution on the agent host, with no LLM involvement. The Policy MCP allowlist is not a default mitigation (mcp_allow_fn defaults to None), so absent an operator-authored allowlist every resolved spec connects.
Affected: mcp_registry/http.py, all versions through 1.0.0. (The https path is sound: httpx defaults to verify=True, follow_redirects=False.)
Fix: require https by default and gate http:// behind a loud explicit opt-in. Defense-in-depth: allowlist the resolved command basename (or require confirmation) before any registry-sourced subprocess spawn. Document the consequence in spec/36.
High Basis: The source's own band: HIGH
0, fixed 1.1.0 (ecosystem)1.1.0
1.1.0pip install --upgrade atomic-agents-stack==1.1.0Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0