CVE-2026-27001

Source
https://cve.org/CVERecord?id=CVE-2026-27001
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-27001.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2026-27001
Aliases
Published
2026-02-19T23:10:07.761Z
Modified
2026-03-03T01:22:51.851927Z
Severity
  • 8.6 (High) CVSS_V4 - 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 Calculator
Summary
OpenClaw: Unsanitized CWD path injection into LLM prompts
Details

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.

Database specific
{
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/27xxx/CVE-2026-27001.json",
    "cna_assigner": "GitHub_M",
    "cwe_ids": [
        "CWE-77"
    ]
}
References

Affected packages

Git / github.com/openclaw/openclaw

Affected ranges

Type
GIT
Repo
https://github.com/openclaw/openclaw
Events
Introduced
0 Unknown introduced commit / All previous commits are affected
Fixed

Database specific

source
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-27001.json"