OpenClaw: Unsanitized CWD path injection into LLM prompts
CVE-2026-27001 · GHSA-2qj5-gwg2-xwc4 · published 2026-02-18 · updated 2026-02-20
- Severity
- High
- CVSS score
- 8.6
- Chance of exploitation (EPSS)
- 0.22%
- Fixed in
- 2026.2.15
- Exploitation No known exploitation
- Automatable No
- Technical impact Total
- CISA SSVC
Prompt injection may alter agent behavior and could lead to unintended tool use or disclosure of sensitive information.
Upgrade openclaw to 2026.2.15 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 workspace path is now sanitized before it is embedded into any LLM prompt output, stripping Unicode control/format characters and explicit line/paragraph separators. Workspace path resolution also applies the same sanitization as defense-in-depth. 6254e96acf16e70ceccc8f9b2abecee44d606f79 Thanks @aether-ai-agent for reporting.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| openclaw | npm | < 2026.2.15 | 2026.2.15 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- 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.