OpenClaw: Unsanitized CWD path injection into LLM prompts
Résumé
OpenClaw: Unsanitized CWD path injection into LLM prompts
Description d'origine
La description telle que publiée par la source (souvent en anglais).
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.
Source: OSV.dev (Open Source Vulnerabilities) NVD GitHub Advisory OSV
Références
- advisory github.com
- advisory github.com
- advisory nvd.nist.gov
- patch github.com
- web github.com