CVE-2026-27001 PUBLISHED

OpenClaw: Unsanitized CWD path injection into LLM prompts

Assigner: GitHub_M
Reserved: 17.02.2026 Published: 19.02.2026 Updated: 19.02.2026

OpenClaw is a personal AI assistant. Prior to version 2026.2.15, OpenClaw embedded the current working directory (workspace path) into the agent system prompt without sanitization. If an attacker can cause OpenClaw to run inside a directory whose name contains control/format characters (for example newlines or Unicode bidi/zero-width markers), those characters could break the prompt structure and inject attacker-controlled instructions. Starting in version 2026.2.15, the workspace path is 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.

Metrics

CVSS Vector: CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CVSS Score: 8.6

Product Status

Vendor openclaw
Product openclaw
Versions
  • Version < 2026.2.15 is affected

References

Problem Types

  • CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection') CWE