Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt Engineering Quality Assurance

Prompt specifications for multi-agent large language model LLM systems carry data contracts and integration logic across many interdependent files but are rarely subjected to structured-inspection rigor. This paper reports a single-system empirical case study of iterative, agent-driven auditing...

EUVD-2026-29286

This issue was addressed by adding an additional prompt for user consent. This issue is fixed in iOS 18.7.9 and iPadOS 18.7.9, iOS 26.5 and iPadOS 26.5, macOS Sequoia 15.7.7, macOS Sonoma 14.8.7, macOS Tahoe 26.5, visionOS 26.5. An app may be able to access user-sensitive data...

GHSA-42H5-H8QH-VV9V MLflow allows an unauthenticated remote attacker to read arbitrary files from the server's filesystem

A vulnerability in the createmodelversion handler of mlflow/server/handlers.py in mlflow/mlflow versions 3.9.0 and earlier allows an unauthenticated remote attacker to read arbitrary files from the server's filesystem. The issue arises when a CreateModelVersion request includes the tag...

EUVD-2026-29180

A vulnerability in the createmodelversion handler of mlflow/server/handlers.py in mlflow/mlflow versions 3.9.0 and earlier allows an unauthenticated remote attacker to read arbitrary files from the server's filesystem. The issue arises when a CreateModelVersion request includes the tag...

MLflow allows an unauthenticated remote attacker to read arbitrary files from the server's filesystem

A vulnerability in the createmodelversion handler of mlflow/server/handlers.py in mlflow/mlflow versions 3.9.0 and earlier allows an unauthenticated remote attacker to read arbitrary files from the server's filesystem. The issue arises when a CreateModelVersion request includes the tag...

CVE-2026-28993

This issue was addressed by adding an additional prompt for user consent. This issue is fixed in iOS 18.7.9 and iPadOS 18.7.9, iOS 26.5 and iPadOS 26.5, macOS Sequoia 15.7.7, macOS Sonoma 14.8.7, macOS Tahoe 26.5, visionOS 26.5. An app may be able to access user-sensitive data...

CVE-2026-2614

A vulnerability in the createmodelversion handler of mlflow/server/handlers.py in mlflow/mlflow versions 3.9.0 and earlier allows an unauthenticated remote attacker to read arbitrary files from the server's filesystem. The issue arises when a CreateModelVersion request includes the tag...

CVE-2026-28993

This issue was addressed by adding an additional prompt for user consent. This issue is fixed in iOS 18.7.9 and iPadOS 18.7.9, iOS 26.5 and iPadOS 26.5, macOS Sequoia 15.7.7, macOS Sonoma 14.8.7, macOS Tahoe 26.5, visionOS 26.5. An app may be able to access user-sensitive data...

CVE-2026-28993

This issue was addressed by adding an additional prompt for user consent. This issue is fixed in iOS 18.7.9 and iPadOS 18.7.9, iOS 26.5 and iPadOS 26.5, macOS Sequoia 15.7.7, macOS Sonoma 14.8.7, macOS Tahoe 26.5, visionOS 26.5. An app may be able to access user-sensitive data...

CVE-2026-28993

An app may be able to access user-sensitive data due to a lack of sufficient consent mechanisms. This issue was addressed by adding an additional prompt for user consent . The vulnerability is fixed in iOS 18.7.9 , iPadOS 18.7.9 , iOS 26.5 , iPadOS 26.5 , macOS Sequoia 15.7.7 , macOS Sonoma 14.8....

CVE-2026-2614 Arbitrary File Read via Prompt Tag Source Validation Bypass in mlflow/mlflow

A vulnerability in the createmodelversion handler of mlflow/server/handlers.py in mlflow/mlflow versions 3.9.0 and earlier allows an unauthenticated remote attacker to read arbitrary files from the server's filesystem. The issue arises when a CreateModelVersion request includes the tag...

CVE-2026-2614

The mlflow software (versions 3.9.0 and earlier) is vulnerable to an arbitrary file read via a path traversal flaw in the _create_model_version() handler of mlflow/server/handlers.py. An unauthenticated remote attacker can bypass source path validation by including the mlflow.prompt.is_prompt tag...

CVE-2026-2614 Arbitrary File Read via Prompt Tag Source Validation Bypass in mlflow/mlflow

A vulnerability in the createmodelversion handler of mlflow/server/handlers.py in mlflow/mlflow versions 3.9.0 and earlier allows an unauthenticated remote attacker to read arbitrary files from the server's filesystem. The issue arises when a CreateModelVersion request includes the tag...

CVE-2026-2614 Arbitrary File Read via Prompt Tag Source Validation Bypass in mlflow/mlflow

A vulnerability in the createmodelversion handler of mlflow/server/handlers.py in mlflow/mlflow versions 3.9.0 and earlier allows an unauthenticated remote attacker to read arbitrary files from the server's filesystem. The issue arises when a CreateModelVersion request includes the tag...

EUVD-2026-29146

OpenClaw before 2026.4.20 contains a guard bypass vulnerability in the agent-facing gateway config.patch and config.apply endpoints that fails to protect operator-trusted settings including sandbox policy, plugin enablement, gateway auth/TLS, hook routing, MCP server configuration, SSRF policy, a...

Duplicate Advisory: OpenClaw: Isolated cron awareness events were recorded as trusted system events

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-57r2-h2wj-g887. This link is maintained to preserve external references. Original Description OpenClaw before 2026.4.20 fails to properly preserve untrusted labels for isolated cron awareness events, allowing...

GHSA-M5J2-R859-R5CV Duplicate Advisory: OpenClaw: Isolated cron awareness events were recorded as trusted system events

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-57r2-h2wj-g887. This link is maintained to preserve external references. Original Description OpenClaw before 2026.4.20 fails to properly preserve untrusted labels for isolated cron awareness events, allowing...

EUVD-2026-29144

OpenClaw before 2026.4.20 fails to properly preserve untrusted labels for isolated cron awareness events, allowing webhook-triggered cron agent output to be recorded as trusted system events. Attackers can exploit this trust-labeling issue to strengthen prompt-injection attacks by rendering...

CVE-2026-45001

OpenClaw before 2026.4.20 contains a guard bypass vulnerability in the agent-facing gateway config.patch and config.apply endpoints that fails to protect operator-trusted settings including sandbox policy, plugin enablement, gateway auth/TLS, hook routing, MCP server configuration, SSRF policy, a...

CVE-2026-44999

OpenClaw before 2026.4.20 fails to properly preserve untrusted labels for isolated cron awareness events, allowing webhook-triggered cron agent output to be recorded as trusted system events. Attackers can exploit this trust-labeling issue to strengthen prompt-injection attacks by rendering...