PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.
CVE-2026-57137
HIGHPre-NVD 8.88.8Elevated
EchelonGraph scoreLOW confidence
This high-severity CVE scores 8.8 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit-prediction score not yet available (the EPSS model rescores nightly; freshly-published CVEs typically appear within 48 hours). GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).
Triggered by: NVD CVSS baseline
Sources: secondary
8.8EG
EchelonGraph verdictPlan a fixSerious severity, but no confirmed exploitation yet.
- High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0%CVSS: 8.8Exploit: Elevated riskExposed: 0
No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.
- CVSS v3
- 8.8
- EG Score
- 8.8(low)
- EG Risk
- 56(Track*)EG Risk 56/100SSVC: Track*
EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).
How it’s computedSeverity88% × 45%Exploitation40% × 40%Automatability0% × 15%Action: Watch closely — could escalate to Attend. - EPSS PROB
- 0%
- EPSS %ILE
- 30%
- KEV
- Not listed
Published
June 18, 2026
Last Modified
September 15, 2026
Advisory Details (3)
Auto-updated Sep 15, 2026🔬 Proof of concept available. Patch available. Sources: github, github_commit, github_release.
github_release Patch Available
PraisonAI v4.6.62
Patch available: MervinPraison/PraisonAI v4.6.62
https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62github_commit Patch Available
commit 6b4b59fbe71a (MervinPraison/PraisonAI)
Patch available: MervinPraison/PraisonAI v4.6.144 (contains commit 6b4b59fbe71a)
https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9github Patch Available🟡 PoC Available
npm Package: AgentLoop onToolCall Approval Runs After Tool Execution · Advisory · MervinPraison/PraisonAI · GitHub
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4Vendor Advisories for CVE-2026-57137(1)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
Affected Packages
(1 across 1 ecosystem)
npm(1)
| Package | Vulnerable range | Fixed in | Dependents |
|---|---|---|---|
| praisonai | — | 1.7.2 | — |
Weakness Classification(3)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 7× in last 7d / 7× in last 30d)
Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.
- 2026-09-18 19:28 UTCEPSS rescore
- 2026-09-17 19:31 UTCEPSS rescore
- 2026-09-16 14:08 UTCEPSS rescore
- 2026-09-16 05:15 UTCEPSS rescore
- 2026-09-15 13:34 UTCEG score recompute
- 2026-09-15 12:53 UTCEG score recompute
- 2026-09-15 11:29 UTCEG score recompute
- 2026-07-30 22:29 UTCEG score recompute
- 2026-07-26 17:45 UTCEG score recompute
- 2026-07-23 03:20 UTCEG score recompute
- 2026-07-20 21:33 UTCEG score recompute
Related CVEs(same CWE)
Same CWE
10 shownCWE-862 · CWE-863
Frequently asked(5)
What is CVE-2026-57137?
CVE-2026-57137 is a high vulnerability published on June 18, 2026. PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback…
When was CVE-2026-57137 disclosed?
CVE-2026-57137 was first published in the National Vulnerability Database on June 18, 2026, with the most recent update on September 15, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-57137 actively exploited?
CVE-2026-57137 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0% probability of exploitation in the next 30 days, which ranks it in the top 70.2% of all scored CVEs.
What is the CVSS score of CVE-2026-57137?
CVE-2026-57137 has a CVSS v3 base score of 8.8 (NVD). The EG score is currently aggregating — additional source signals are being incorporated as they become available..
How do I remediate CVE-2026-57137?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-57137, EchelonGraph cross-links them in the Vendor Advisories panel below — those typically contain the canonical remediation steps, fixed version numbers, and any vendor-specific mitigations.
Dependency Blast Radius
See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-57137
Is Your Infrastructure Affected by CVE-2026-57137?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.