PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-57118 MervinPraison CVE debrief

CVE-2026-57118 is a critical vulnerability in PraisonAI's AgentTeam.launch feature, exposing unauthenticated remote agent listing and invocation endpoints. This vulnerability allows unauthenticated clients to enumerate agents, consume model resources, access connected private context, and trigger agent tools or workflow side effects. The vulnerability is fixed in praisonaiagents 1.6.59.

Vendor
MervinPraison
Product
PraisonAI
CVSS
CRITICAL 9.8
CISA KEV
Not listed in stored evidence
Original CVE published
2026-10-12
Original CVE updated
2026-10-12
Advisory published
2026-10-12
Advisory updated
2026-10-12

Who should care

Defenders responsible for PraisonAI deployments should assess exposure and prioritize upgrading to praisonaiagents 1.6.59 or later. Security teams should monitor for suspicious activity and agent enumeration attempts.

Why it matters

CVE-2026-57118 is a critical vulnerability in PraisonAI's AgentTeam.launch feature, allowing unauthenticated remote agent listing and invocation. Defenders should prioritize verifying exposure and upgrading to praisonaiagents 1.6.59 or later. Limited information is available on potential exploitation or victim impact, requiring verification from official sources.

  • Unauthenticated remote agent listing and enumeration
  • Consumption of model resources by unauthorized clients
  • Access to connected private context without authentication
  • Triggering of agent tools or workflow side effects without authorization

Technical summary

The vulnerability is caused by a lack of access-control checks in AgentTeam.launch and the Agents alias, allowing unauthenticated clients to list agents, consume model resources, access connected private context, and trigger agent tools or workflow side effects. This issue affects PraisonAI's AgentTeam.launch feature, enabling unauthenticated remote agent listing and invocation endpoints. Defenders should prioritize verifying exposure and upgrading to praisonaiagents 1.6.59 or later. Inventory checks and monitoring for suspicious activity are recommended.

Defensive priority

Defenders should prioritize verifying exposure of PraisonAI AgentTeam.launch and upgrading to praisonaiagents 1.6.59 or later. Inventory checks and monitoring for suspicious activity are recommended.

Recommended defensive actions

  • Verify exposure of PraisonAI AgentTeam.launch in your environment
  • Upgrade to praisonaiagents 1.6.59 or later
  • Monitor for suspicious activity and agent enumeration attempts
  • 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
  • Review the supplied official advisory or CVE record to validate affected scope, severity, and vendor guidance

Evidence notes

The CVE record and source item provide details on the vulnerability, affected versions, and fixed versions. However, limited information is available on potential exploitation or victim impact. Defenders should verify exposure of PraisonAI AgentTeam.launch and review official advisories for affected scope and severity. Limited source information requires defensive validation.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-57118 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-57118

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-57118 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-57118

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

  • PraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpoints

    Unverified legacy reference

    URL: https://raw.githubusercontent.com/CVEProject/cvelistV5/main/cves/2026/57xxx/CVE-2026-57118.json

    cve_program_cvelist_v5

  • Source reference

    Unverified legacy reference

    URL: https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-x8cv-xmq7-p8xp

    Supplemental source - x_refsource_CONFIRM

  • Source reference

    Unverified legacy reference

    URL: https://github.com/MervinPraison/PraisonAI/commit/b4270173d4123fb1ee8910588f0896668ee21b59

    Supplemental source - x_refsource_MISC

  • Source reference

    Unverified legacy reference

    URL: https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59

    Supplemental source - x_refsource_MISC

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.