Local file disclosure via unbounded Editor paths
Published Aug 6, 2026 · Updated Aug 6, 2026
Path traversal in MetaGPT 0.8.0 through 0.8.2 allows local users to read files outside the configured project workspace. Editor.read passes its path through _try_fix_path, which preserves absolute paths and joins relative paths without verifying that the resolved path stays under working_dir. A user who can steer DataInterpreter task execution can disclose any host file readable by the MetaGPT process, including system and user configuration data.
Summary
What happened
Path traversal in MetaGPT 0.8.0 through 0.8.2 allows local users to read files outside the configured project workspace. Editor.read passes its path through _try_fix_path, which preserves absolute paths and joins relative paths without verifying that the resolved path stays under working_dir. A user who can steer DataInterpreter task execution can disclose any host file readable by the MetaGPT process, including system and user configuration data.
The record
- CVE
- CVE-2026-19059
- Published
- Aug 6, 2026
- Updated
- Aug 6, 2026
- Vendor
- Foundation Agents
- Product
- MetaGPT
- Classifications
- CWE-22, T1005
- Attack vector
- local
- Privileges
- authenticated
Timeline
How it unfolded
- Aug 6, 2026CVE publishedPublication date reported by the CVE source.
- Aug 6, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0.8.0
- Affected versionversion=0.8.1
- Affected versionversion=0.8.2
What conditions does exploitation require?
What is affected?
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Editor workspace-confinement deterministic proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo