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
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.
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 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.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| openclaw | npm | < 2026.2.13 | 2026.2.13 |
- CriticalMarimo: Pre-Auth Remote Code Execution via Terminal WebSocket Authentication BypassmarimoExploited
- CriticalLangflow CORS misconfiguration enables Account Takeover and RCElangflowExploited
- HighLiteLLM: MCP Authentication Bypass via OAuth2 Passthrough FallbacklitellmExploited
- HighLangflow: IDOR Vulnerability in `/api/v1/responses` Endpoint Allows Authenticated Attackers to Access Another User's FlowlangflowExploited
- CriticalTodoist MCP Server: Browser DNS rebinding lets websites write and delete Todoist data through local MCP server@doist/todoist-mcp
- CriticalLangflow: Unauthenticated Flow Execution via Webhook Authentication Bypasslangflow
- CriticalOpenClaw: QQBot admin commands could skip DM-only and allowFrom policyopenclaw
- CriticalOpenClaw: Feishu webhook and card-action validation now fail closedopenclaw
- CriticalOpenClaw: Gateway HTTP endpoints re-resolve bearer auth after SecretRef rotationopenclaw
- CriticalOpenClaw: Sandbox escape via TOCTOU race in remote FS bridge readFileopenclaw
- CriticalOpenClaw: Heartbeat context inheritance bypasses sandbox via senderIsOwner escalationopenclaw
- CriticalOpenClaw has a CWD `.env` environment variable injection which bypasses host-env policy and allows config takeoveropenclaw
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.