UTC
High

OpenClaw inter-session prompts could be treated as direct user instructions

GHSA-w5c7-9qqw-6645 · published 2026-02-18

Severity
High
CVSS score
7.1
Chance of exploitation (EPSS)
No CVE
Fixed in
2026.2.13
What it is

A delegated or internal session could inject instructions into another session that appeared equivalent to externally-originated user input. This is an instruction-provenance confusion issue (confused-deputy style), which can lead to unintended privileged behavior in workflows that trust role: "user" as a sole authority signal.

What to do

Upgrade openclaw to 2026.2.13 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.

OpenClaw now carries explicit input provenance end-to-end for routed prompts. Key changes: Added structured provenance model (inputProvenance) with kind values including intersession. sessionssend and agent-to-agent steps now set inter-session provenance when invoking target runs. Provenance is persisted on user messages as for provider compatibility). Transcript readers and memory helpers were updated to respect provenance and avoid treating inter-session prompts as external user-originated input. Runtime context rebuilding now annotates inter-session turns with an explicit in-memory marker ([Inter-session message]) for clearer model-side disambiguation.

If you cannot upgrade yet

If immediate upgrade is not possible: Disable or restrict sessions_send in affected environments. Do not use role alone as an authority boundary; require provenance-aware checks in orchestration logic.

Affected
PackageRegistryAffectedFixed in
openclawnpm< 2026.2.132026.2.13

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). 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].