Arbitrary file read and write via multiedit
Published Sep 14, 2026 · Updated Sep 14, 2026
Path traversal in PraisonAI before 4.6.62 allows attackers to read or overwrite process-accessible files through multiedit. The multiedit implementation passes its LLM-controlled filepath directly to open for reads and writes without traversal rejection, symlink resolution, protected-path checks, or workspace confinement. Exploitation requires influence over agent tool arguments and exposes readable secrets or permits persistent tampering with writable files.
Summary
What happened
Path traversal in PraisonAI before 4.6.62 allows attackers to read or overwrite process-accessible files through multiedit. The multiedit implementation passes its LLM-controlled filepath directly to open for reads and writes without traversal rejection, symlink resolution, protected-path checks, or workspace confinement. Exploitation requires influence over agent tool arguments and exposes readable secrets or permits persistent tampering with writable files.
The record
- CVE
- CVE-2026-57145
- Published
- Sep 14, 2026
- Updated
- Sep 14, 2026
- Vendor
- PraisonAI
- Product
- PraisonAI
- Classifications
- CWE-22, T1005, T1565.001
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 14, 2026CVE publishedPublication date reported by the CVE source.
- Sep 14, 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=< 4.6.62
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
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
- multiedit arbitrary file read and write 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