PatchSiren cyber security CVE debrief
CVE-2026-57142 MervinPraison CVE debrief
CVE-2026-57142 debrief: PraisonAI recipe workflow policy bypass allows untrusted recipes to execute dangerous tools, potentially leading to security breaches. PraisonAI users and administrators should assess exposure and upgrade to version 4.6.61 or later to prevent potential security breaches. The vulnerability allows untrusted recipes to bypass safety features and execute dangerous tools, which may lead to security breaches. Verification of PraisonAI version and recipe execution policies is necessary. Remediation requires upgrading to PraisonAI version 4.6.61 or later and reviewing untrusted recipe execution policies.
- Vendor
- MervinPraison
- Product
- PraisonAI
- CVSS
- HIGH 7.8
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-10-23
- Original CVE updated
- 2026-10-29
- Advisory published
- 2026-10-23
- Advisory updated
- 2026-10-29
Who should care
PraisonAI users and administrators should assess exposure and upgrade to version 4.6.61 or later to prevent potential security breaches. PraisonAI operators, platform administrators, and security teams should review and restrict untrusted recipe execution policies. Verification of PraisonAI version and recipe execution policies is necessary.
Why it matters
CVE-2026-57142 allows untrusted PraisonAI recipes to execute dangerous tools, bypassing safety features. PraisonAI users and administrators should assess exposure and upgrade to version 4.6.61 or later to prevent potential security breaches.
- Untrusted recipes can execute dangerous tools, potentially leading to security breaches
- Bypass of safety features may allow attackers to exploit the vulnerability
- Verification of PraisonAI version and recipe execution policies is necessary
- Remediation requires upgrading to PraisonAI version 4.6.61 or later
Technical summary
PraisonAI recipe execution has a dangerous-tool policy that can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml. This issue has been patched in version 4.6.61. The vulnerability allows untrusted recipes to execute dangerous tools, potentially leading to security breaches. PraisonAI users and administrators should assess exposure and upgrade to version 4.6.61 or later to prevent potential security breaches. The bypass allows untrusted recipes to execute dangerous tools, which may lead to security breaches.
Defensive priority
High priority for PraisonAI users to assess exposure and upgrade to version 4.6.61 or later
Recommended defensive actions
- Assess exposure by checking if PraisonAI version is between 4.5.87 and 4.6.61
- Upgrade to PraisonAI version 4.6.61 or later
- Review and restrict untrusted recipe execution in PraisonAI
- Verify PraisonAI version and recipe execution policies
- Review compensating controls for exposed systems while remediation is scheduled and verified
- Check relevant monitoring, detection, and logs for exposed assets that need extra review
- Track exceptions, retest remediated assets, and close the item only after evidence is documented
Evidence notes
Official CVE Program record and NIST NVD detail page provide vulnerability metadata. Source item from cve_program_cvelist_v5 provides detailed vulnerability description. The CVE record was published on 2026-10-23T12:07:46.547Z and has not been modified since then. The vulnerability affects PraisonAI versions 4.5.87 to before version 4.6.61. The issue has been patched in version 4.6.61. PraisonAI users and administrators should assess exposure and upgrade to version 4.6.61 or later.
Sources and references
Verified primary and authoritative sources
-
CVE-2026-57142 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2026-57142
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2026-57142 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2026-57142
NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.
Supplemental references
-
PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools
Unverified legacy reference
URL: https://raw.githubusercontent.com/CVEProject/cvelistV5/main/cves/2026/57xxx/CVE-2026-57142.json
cve_program_cvelist_v5
-
Source reference
Unverified legacy reference
URL: https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2
Supplemental source - x_refsource_CONFIRM
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.