OpenClaw macOS deep link confirmation truncation can conceal executed agent message
CVE-2026-26320 · GHSA-7q2j-c4q5-rm27 · published 2026-02-17 · updated 2026-02-20
- Severity
- High
- CVSS score
- 7.1
- Chance of exploitation (EPSS)
- 0.48%
- Fixed in
- 2026.2.14
- Exploitation No known exploitation
- Automatable Yes
- Technical impact Partial
- CISA SSVC
If a user runs the deep link, the agent may perform actions that can lead to arbitrary command execution depending on the user's configured tool approvals/allowlists. This is a social-engineering mediated vulnerability: the confirmation prompt could be made to misrepresent the executed message.
Upgrade openclaw to 2026.2.14 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.
2026.2.14.
Do not approve unexpected "Run OpenClaw agent?" prompts triggered while browsing untrusted sites. Use unattended deep links only with a valid key for trusted personal automations.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| openclaw | npm | >= 2026.2.6-0, < 2026.2.14 | 2026.2.14 |
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- Criticaln8n Vulnerable to Remote Code Execution via Expression Injectionn8n, n8nExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLangflow affected by Remote Code Execution via validate_code() exec()langflowExploited
- CriticalJupyter MCP Server: Browser DNS rebinding can hijack the Jupyter backend through management routesjupyter-mcp-server
- Criticalmem0ai Databricks vector store vulnerable to SQL injectionmem0ai
- 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.