Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-55533 – Authentication Bypass (Fail-Open) – PraisonAI Recipe Server < 4.6.58

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-55533 is an authentication fail-open vulnerability in PraisonAI, an open-source multi-agent AI orchestration framework. When the PraisonAI Recipe HTTP server is configured to use API-key or JWT authentication but the corresponding secret (PRAISONAI_API_KEY or PRAISONAI_JWT_SECRET) is not actually set in the environment, the server silently falls back to accepting unauthenticated requests instead of rejecting them. This affects PraisonAI versions prior to 4.6.58 and carries a CVSS v3.1 base score of 8.2 (High).

Technical details

  • Root cause: The create_auth_middleware() function in the PraisonAI Recipe server is designed to enforce API-key or JWT-based authentication, but when the operator sets auth=api-key or auth=jwt without configuring the matching secret environment variable, the middleware fails open and permits the request rather than denying it.
  • Trigger conditions: A Recipe server must be deployed with authentication nominally enabled (auth != "none") but missing the required secret — a misconfiguration the CLI’s safety check does not catch, since it only verifies that auth mode is not "none" and never confirms a secret is actually present.
  • Attack vector: Network-based (AV:N), requiring no privileges (PR:N) and no user interaction (UI:N). An attacker only needs network access to an externally reachable Recipe server instance.
  • Impact: Unauthenticated attackers can issue POST requests to sensitive endpoints such as /v1/recipes/run (and reportedly /v1/recipes/stream), allowing arbitrary execution of agent "recipes" on the server. This yields high integrity impact (I:H) — attackers can trigger unauthorized workflow/agent execution — with low confidentiality impact (C:L) and no direct availability impact (A:N) per the CVSS vector.

Affected software

  • Product: PraisonAI (MervinPraison/PraisonAI)
  • Vulnerable versions: Prior to 4.6.58 (confirmed vulnerable at 4.6.52)
  • Fixed version: 4.6.58 and later

Severity

  • CVSS v3.1 Base Score: 8.2 (High)
  • Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N
  • Weaknesses: CWE-287 (Improper Authentication), CWE-306 (Missing Authentication for Critical Function)

Mitigation and recommended actions

  • Immediate: Upgrade PraisonAI to version 4.6.58 or later, which corrects the authentication middleware so that requests are rejected when a required secret is not configured.
  • If immediate patching is not possible:
    • Verify that any Recipe server bound to a non-localhost interface has PRAISONAI_API_KEY or PRAISONAI_JWT_SECRET explicitly and correctly set before relying on auth=api-key/auth=jwt for protection.
    • Restrict network exposure of Recipe server endpoints (e.g., /v1/recipes/run) to trusted internal networks or via a VPN/firewall/allowlist until patched.
    • Audit deployment configurations to confirm authentication is genuinely enforced rather than assuming CLI safety checks (auth != "none") guarantee credential validation.
    • Monitor Recipe server logs for unauthenticated POST requests to recipe execution endpoints as a possible indicator of exploitation attempts.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge