Cyber Resilience

CVE-2026-61439

Public PoC
Published
11 July 2026
Modified
14 July 2026
CVSS Score v4 8.7
Click a component to see what it means
Raw vectorCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
EPSS Score 0.0026 18th percentile
Risk Priority 55 floored blend · peak EPSS

Summary

CVE-2026-61439 is a high-severity Initialization of a Resource with an Insecure Default (CWE-1188) vulnerability. Its CVSS base score is 8.7 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 18th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the LLM/Generative AI Risks risk domain.

The strongest mitigations our analysis identified map to CM-6 (Configuration Settings) and SI-10 (Information Input Validation) — see the control section below for these in your framework.

EU & UK References

Vulnerability Data

PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financial manipulation that…

more

trigger HIGH severity detection but are logged without blocking, enabling system prompt extraction and unauthorized tool invocations.

CWE(s)
CWE-1188

AI Security AnalysisAI

AI Category
AI Agent Protocols and Integrations
Risk Domain
LLM/Generative AI Risks
OWASP Top 10 for LLMs 2025
None mapped
AI-specific weaknesses CR
CWE-1434
  • CWE-1434 — Insecure default inference/safety parameter (block threshold) allows prompt injection.
Mapped by Cyber Resilience · not in NVD. Poisoning and extraction cases are routed to MITRE ATLAS instead of a synthetic CWE.
Classification Reason
Matched keywords: prompt injection, prompt injection

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
attack.mitre.org →
T1059 Command and Scripting Interpreter Execution
Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.
attack.mitre.org →
Why these techniques?

Misconfigured prompt injection threshold directly enables bypass of defenses on a public-facing AI application (T1190), permitting successful instruction overrides that result in unauthorized tool/command execution (T1059).

Confidence: HIGH · MITRE ATT&CK Enterprise v19.0

CVEs Like This One

CVE-2026-44109Shared CWE-1188
CVE-2025-66414Shared CWE-1188
CVE-2026-47393Shared CWE-1188
CVE-2025-2129Shared CWE-1188
CVE-2026-32965Shared CWE-1188
CVE-2025-56332Shared CWE-1188
CVE-2025-66416Shared CWE-1188
CVE-2026-35672Shared CWE-1188
CVE-2026-40994Shared CWE-1188
CVE-2026-34742Shared CWE-1188

Affected Assets

—
PraisonAI
inferred from references and description; NVD did not file a CPE for this CVE

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)
  • SI-10 Information Input Validation
  • CM-6 Configuration Settings
  • SI-3 Malicious Code Protection
Detect
Catch it (NIST detect / respond)
  • SI-3 Malicious Code Protection
Harden
Shrink the surface (DISA STIG)
  • 13 hardening rules · 7 OS baselines
Validate
Prove the fix (OWASP ASVS)
  • V14.3.2
  • V6.3.2
  • V11.3.1
  • V13.2.3

Mitigating Controls (NIST 800-53 r5) AI

SI-10 Information Input Validation good match
prevent

Directly enforces validation of inputs to reject or sanitize HIGH-severity prompt injection attempts before they reach the model or tools.

CM-6 Configuration Settings good match
prevent

Requires secure configuration of the block threshold so that HIGH-severity detections actively block rather than defaulting to log-only behavior.

SI-3 Malicious Code Protection partial match
preventdetect

Provides mechanisms to detect and block malicious inputs such as prompt injections that would otherwise allow system prompt extraction and unauthorized tool use.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-01 full match
prevents

Hardened baselines and configuration management directly replace insecure defaults with secure settings.

PR.PS-06 mostly match
prevents

Secure development practices include designing products with secure defaults rather than insecure ones.

ID.RA-09 partial match
prevents

Pre-acquisition integrity checks can reject products known to ship with insecure defaults.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

A.8.9 Configuration management mostly match
prevents

Mandating secure baseline templates and immediate replacement of vendor defaults directly stops systems from being deployed with insecure factory settings that attackers can exploit.

A.8.32 Change management partial match
prevents

Requiring documented specification, testing, and acceptance of changes ensures that new or modified components are not initialized with insecure default settings that would otherwise be left in production.

A.5.21 Managing information security in the ICT supply chain none match
none

Requiring suppliers to document secure configuration and implemented security functions reduces the likelihood that products will be initialised with insecure default settings.

Hardening callouts derived

Configuration rules from DISA STIG baselines that reduce the attack surface for weaknesses of the type cited by this CVE. Derived transitively via CVE→CWE→STIG over `controls_xwalks` (authoritative rows only).

Oracle Linux 8 (1 rule)
  • V-248823 OL 8 must not have the telnet-server package installed. via CWE-1188
RHEL 7 (1 rule)
  • V-204627 SNMP community strings on the Red Hat Enterprise Linux operating system must be changed from the default. via CWE-1188
Ubuntu 22.04 (1 rule)
  • V-260529 Ubuntu 22.04 LTS must be configured so that remote X connections are disabled, unless to fulfill documented and validated mission requirements. via CWE-1188
Ubuntu 24.04 (1 rule)
  • V-270708 Ubuntu 24.04 LTS must be configured so that remote X connections are disabled, unless to fulfill documented and validated mission requirements. via CWE-1188
Windows Server 2019 (1 rule)
  • V-205741 Windows Server 2019 Active Directory Group Policy objects must have proper access control permissions. via CWE-1188
Windows Server 2022 (1 rule)
  • V-254393 Windows Server 2022 Active Directory Group Policy objects must have proper access control permissions. via CWE-1188

References