PatchSiren cyber security CVE debrief
CVE-2026-55540 MervinPraison CVE debrief
CVE-2026-55540 is a vulnerability in PraisonAI, a multi-agent teams system, where the is_path_within_directory() function uses os.path.abspath() instead of os.path.realpath() for workspace boundary checks. This allows a symlink within the workspace to point outside and pass the check, enabling read_file and other tools to access files outside the configured workspace. The issue is fixed in version 4.6.58.
- Vendor
- MervinPraison
- Product
- PraisonAI
- CVSS
- HIGH 7.1
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-08-25
- Original CVE updated
- 2026-09-09
- Advisory published
- 2026-08-25
- Advisory updated
- 2026-09-09
Who should care
Defenders and administrators using PraisonAI should verify and update to version 4.6.58 or later to prevent unauthorized file access. They should review workspace configurations, restrict access to workspace directories, and monitor for suspicious file access patterns. Security teams should also review compensating controls for exposed systems and track exceptions and retest remediated assets.
Why it matters
CVE-2026-55540 allows unauthorized file access in PraisonAI; defenders should verify and update to version 4.6.58 or later.
- Potential unauthorized file access
- Need to verify and update PraisonAI version
- Monitor for suspicious file access patterns
Technical summary
The is_path_within_directory() function in PraisonAI uses os.path.abspath() instead of os.path.realpath() for workspace boundary checks, allowing a symlink to bypass the check and access files outside the workspace. This issue is fixed in version 4.6.58, which addresses the vulnerability by using the correct function for workspace boundary checks. The fix prevents unauthorized file access by ensuring that symlinks within the workspace cannot point outside and bypass the check. Defenders should prioritize verifying and updating PraisonAI to version 4.6.58 or later.
Defensive priority
Defenders should prioritize verifying and updating PraisonAI to version 4.6.58 or later to prevent unauthorized file access.
Recommended defensive actions
- Verify PraisonAI version and update to 4.6.58 or later
- Review and restrict access to workspace directories
- Monitor for suspicious file access patterns
- Review compensating controls for exposed systems
- Check relevant monitoring, detection, and logs for exposed assets
- Track exceptions and retest remediated assets
- Confirm whether affected product deployments exist in managed environments
Evidence notes
The CVE record and NVD entry provide details on the vulnerability, its impact, and the fix in version 4.6.58. Defenders should verify PraisonAI version and review workspace configurations to prevent unauthorized file access. The is_path_within_directory() function's use of os.path.abspath() instead of os.path.realpath() allows symlinks to bypass checks, enabling access to files outside the workspace. Evidence from the CVE record and NVD entry suggests that the fix in version 4.6.58 addresses this issue.
Sources and references
Verified primary and authoritative sources
-
CVE-2026-55540 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2026-55540
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2026-55540 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2026-55540
NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.
Supplemental references
-
Source reference
Unverified legacy reference
URL: https://github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828fd0141612e1
-
Source reference
Unverified legacy reference
URL: https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58
-
Source reference
Unverified legacy reference
URL: https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-ch89-h4r2-c8f8
Methodology and review provenance
AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.