CVE-2026-57145: CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in MervinPraison PraisonAI
PraisonAI is a multi-agent teams system. Prior to 4.6.62, src/praisonai/praisonai/tools/multiedit.py passes the LLM-controlled filepath parameter directly to open for reading and writing without traversal rejection, symlink resolution, a workspace boundary, or protected-path checks. Prompt-influenced agents can read files through edit and diff behavior or overwrite files accessible to the process, exposing secrets and enabling persistence or application tampering. This issue is fixed in 4.6.62.
AI Analysis
Technical Summary
PraisonAI versions before 4.6.62 contain a path traversal vulnerability (CWE-22) in the multiedit.py tool where the LLM-controlled filepath parameter is used directly in file open calls without checks for traversal, symlink resolution, or workspace boundaries. This flaw enables prompt-influenced agents to read or overwrite files accessible to the process, risking exposure of secrets and unauthorized modification. The vulnerability has a CVSS 3.1 score of 9.1, indicating critical severity. The issue is resolved in version 4.6.62.
Potential Impact
An attacker can exploit this vulnerability to read sensitive files or overwrite files accessible to the PraisonAI process. This can lead to exposure of confidential information, unauthorized persistence mechanisms, or tampering with the application, potentially compromising system integrity and confidentiality.
Mitigation Recommendations
Upgrade PraisonAI to version 4.6.62 or later, where this vulnerability is fixed. No other mitigations are indicated or necessary once the official fix is applied.
CVE-2026-57145: CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in MervinPraison PraisonAI
Description
PraisonAI is a multi-agent teams system. Prior to 4.6.62, src/praisonai/praisonai/tools/multiedit.py passes the LLM-controlled filepath parameter directly to open for reading and writing without traversal rejection, symlink resolution, a workspace boundary, or protected-path checks. Prompt-influenced agents can read files through edit and diff behavior or overwrite files accessible to the process, exposing secrets and enabling persistence or application tampering. This issue is fixed in 4.6.62.
CVSS v3.1
Score 9.1critical
Affected software
MervinPraison
PraisonAI
pkg:github/mervinpraison/PraisonAIRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
PraisonAI versions before 4.6.62 contain a path traversal vulnerability (CWE-22) in the multiedit.py tool where the LLM-controlled filepath parameter is used directly in file open calls without checks for traversal, symlink resolution, or workspace boundaries. This flaw enables prompt-influenced agents to read or overwrite files accessible to the process, risking exposure of secrets and unauthorized modification. The vulnerability has a CVSS 3.1 score of 9.1, indicating critical severity. The issue is resolved in version 4.6.62.
Potential Impact
An attacker can exploit this vulnerability to read sensitive files or overwrite files accessible to the PraisonAI process. This can lead to exposure of confidential information, unauthorized persistence mechanisms, or tampering with the application, potentially compromising system integrity and confidentiality.
Mitigation Recommendations
Upgrade PraisonAI to version 4.6.62 or later, where this vulnerability is fixed. No other mitigations are indicated or necessary once the official fix is applied.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-06-24T01:45:48.697Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6aa80fff55bf5e2cf53beb20
Added to database: 09/14/2026, 15:17:19 UTC
Last enriched: 09/14/2026, 15:31:27 UTC
Last updated: 09/15/2026, 03:07:00 UTC
Views: 15
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.