PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-55533 MervinPraison CVE debrief

CVE-2026-55533 is a high-severity vulnerability in PraisonAI, a multi-agent teams system. The issue allows unauthenticated POST /v1/recipes/run requests despite authentication being enabled. This vulnerability is fixed in version 4.6.58. Defenders should assess exposure, verify authentication configurations, and apply the fixed version to mitigate potential operational impacts. The vulnerability's high severity indicates significant risk, especially for externally bound Recipe servers.

Vendor
MervinPraison
Product
PraisonAI
CVSS
HIGH 8.2
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 responsible for PraisonAI systems, especially those with externally bound Recipe servers, should assess exposure and verify authentication configurations. This includes reviewing system configurations, monitoring for potential unauthenticated requests, and applying the fixed version to mitigate potential operational impacts. Prioritization is crucial due to the vulnerability's high severity and potential for significant operational impact.

Why it matters

CVE-2026-55533 is a high-severity vulnerability in PraisonAI that allows unauthenticated POST /v1/recipes/run requests. Defenders should prioritize verifying exposure, assessing authentication configurations, and applying the fixed version.

  • Verify authentication configuration for PraisonAI systems
  • Assess exposure of externally bound Recipe servers
  • Apply version 4.6.58 or later to fix the vulnerability
  • Monitor for potential unauthenticated requests

Technical summary

The create_auth_middleware() function in PraisonAI allows requests when auth=api-key lacks PRAISONAI_API_KEY or JWT authentication lacks PRAISONAI_JWT_SECRET. This enables an externally bound Recipe server to accept unauthenticated POST /v1/recipes/run requests despite authentication being enabled. The vulnerability's technical details indicate a significant risk due to the potential for unauthorized access. Defenders should prioritize verifying exposure and assessing authentication configurations to mitigate this risk.

Defensive priority

Defenders should prioritize verifying exposure of PraisonAI systems, especially those with externally bound Recipe servers, and assess the need for authentication configuration updates.

Recommended defensive actions

  • Verify PraisonAI system exposure, especially those with externally bound Recipe servers
  • Assess authentication configuration and update as necessary
  • Apply version 4.6.58 or later to fix the vulnerability
  • Monitor for potential unauthenticated requests
  • 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

The CVE record and NVD entry provide details on the vulnerability, its impact, and the fixed version. However, additional information on potential exploitation or affected systems is limited. Defenders should verify exposure, assess authentication configurations, and apply version 4.6.58 or later. The externally bound Recipe server's ability to accept unauthenticated requests poses a significant risk. Limited source detail suggests cautious verification and defensive measures are necessary.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-55533 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-55533

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

  • CVE-2026-55533 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-55533

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

Supplemental references

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.