openclaw
Affected
- introduced
0, fixed2026.2.15(semver)
Fixed versions
2026.2.15
Fix
- Fixed version
2026.2.15npm install [email protected]
Advisory
Also known as: CVE-2026-27001
OpenClaw: Unsanitized CWD path injection into LLM prompts
Overview
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.
Impact
Prompt injection may alter agent behavior and could lead to unintended tool use or disclosure of sensitive information.
Affected Packages / Versions
openclaw (npm)< 2026.2.15 (latest published vulnerable version as of 2026-02-16: 2026.2.14)>= 2026.2.15Fix
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.
Fix Commit(s)
6254e96acf16e70ceccc8f9b2abecee44d606f79Thanks @aether-ai-agent for reporting.
High Basis: The source's own band: HIGH
0, fixed 2026.2.15 (semver)2026.2.15
2026.2.15npm install [email protected]Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0