CVE-2026-102610
fast-agent is a framework for building, running, and evaluating AI …
fast-agent is a framework for building, running, and evaluating AI agents with Model Context Protocol support. Prior to 0.7.21, fast-agent serve uses HTTP transport bound to 0.0.0.0 on port 8000 without authentication, allowing any network client that can reach the /mcp endpoint to invoke the exposed agent tool. When the server is started with --shell, the agent can call the local execute tool implemented by tools/local_shell_executor.py, so an unauthenticated remote client can cause operating-system commands to run as the server user; without --shell, the client can still consume the operator's model and configured MCP tools. The defaults are defined in cli/commands/serve.py and mcp/server/agent_server.py, and the non-interactive server permission prompt does not prevent the described access. This issue is fixed in version 0.7.21.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/evalstate/fast-agent/commit/ba99f89c3ec7f1ef1c8b1ebce381c12b60dfea29
- github.com/evalstate/fast-agent/pull/828
- github.com/evalstate/fast-agent/releases/tag/v0.7.21
- github.com/evalstate/fast-agent/security/advisories/GHSA-9vhv-g5hf-m7m7
- nvd.nist.gov/vuln/detail/CVE-2026-102610
- github.com/advisories/GHSA-9vhv-g5hf-m7m7
- nvd.nist.gov/vuln/detail/CVE-2026-102610
- cve.org/CVERecord?id=CVE-2026-102610
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.