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.
Prompt injection may alter agent behavior and could lead to unintended tool use or disclosure of sensitive information.
openclaw (npm)< 2026.2.15 (latest published vulnerable version as of 2026-02-16: 2026.2.14)>= 2026.2.15The 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.
6254e96acf16e70ceccc8f9b2abecee44d606f79Thanks @aether-ai-agent for reporting.
{
"github_reviewed": true,
"github_reviewed_at": "2026-02-18T22:42:29Z",
"cwe_ids": [
"CWE-77"
],
"severity": "HIGH",
"nvd_published_at": "2026-02-20T00:16:16Z"
}