UTC
Medium

Session filename generation could regain denied tools

GHSA-5fwv-rrvp-8xvr · published 2026-09-11

Severity
Medium
CVSS score
5.3
Chance of exploitation (EPSS)
No CVE
Fixed in
2026.8.1
What it is

When session-memory filename generation was enabled for an agent reachable by lower-trust senders, model-mediated instructions could invoke tools outside that sender's effective policy. Demonstrated impact included creating persistent scheduled work. Practical impact depended on the model following the injected instruction and on which tools the helper exposed.

What to do

Upgrade openclaw to 2026.8.1 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

The first stable patched version is 2026.8.1.

If you cannot upgrade yet

Upgrade to [email protected] or later. Before upgrading, disable session-memory filename generation for agents reachable by lower-trust senders.

Affected
PackageRegistryAffectedFixed in
openclawnpm< 2026.8.12026.8.1

The impact, patch and workaround text comes from the advisory, shortened (published by OpenClaw). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].