Arbitrary Code Injection

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Arbitrary Code Injection via the createguardrail, updateguardrail, deleteguardrail, and patchguardrail handlers in the guardrails API. An attacker can upload or modify cust...

CVE-2026-59821

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to creat...

CVE-2026-15154

A flaw was found in guardrails-detectors, a component of Red Hat OpenShift AI. This vulnerability, known as Regular Expression Denial of Service ReDoS, allows a remote attacker to provide specially crafted regular expressions to the public detection API. This can cause catastrophic backtracking,...

CVE-2026-15154 Guardrails-detectors: guardrails-detectors: unauthenticated regular-expression denial of service (redos) via detector_params.regex

A flaw was found in guardrails-detectors, a component of Red Hat OpenShift AI. This vulnerability, known as Regular Expression Denial of Service ReDoS, allows a remote attacker to provide specially crafted regular expressions to the public detection API. This can cause catastrophic backtracking,...

EUVD-2026-42382

A flaw was found in guardrails-detectors, a component of Red Hat OpenShift AI. This vulnerability, known as Regular Expression Denial of Service ReDoS, allows a remote attacker to provide specially crafted regular expressions to the public detection API. This can cause catastrophic backtracking,...

CVE-2026-15154

Technical details (affected products/versions, root cause specifics, remediation) are not publicly provided in the supplied documents. Monitor for updates to confirm scope, impact and fixes for CVE-2026-15154 regarding guardrails-detectors in Red Hat OpenShift AI.

CVE-2026-15154 Guardrails-detectors: guardrails-detectors: unauthenticated regular-expression denial of service (redos) via detector_params.regex

A flaw was found in guardrails-detectors, a component of Red Hat OpenShift AI. This vulnerability, known as Regular Expression Denial of Service ReDoS, allows a remote attacker to provide specially crafted regular expressions to the public detection API. This can cause catastrophic backtracking,...

CVE-2026-15154

A flaw was found in guardrails-detectors, a component of Red Hat OpenShift AI. This vulnerability, known as Regular Expression Denial of Service ReDoS, allows a remote attacker to provide specially crafted regular expressions to the public detection API. This can cause catastrophic backtracking,...

CVE-2026-15154

A flaw was found in guardrails-detectors, a component of Red Hat OpenShift AI. This vulnerability, known as Regular Expression Denial of Service ReDoS, allows a remote attacker to provide specially crafted regular expressions to the public detection API. This can cause catastrophic backtracking,...

CVE-2026-59821

CVE-2026-59821 affects LiteLLM , an AI Gateway proxy server for LLM APIs. The Custom Code Guardrails production create and update endpoints (POST /guardrails, PUT /guardrails/{guardrail_id}) failed to apply the same sandboxing and validation used by the test endpoint, allowing a privileged user t...

CVE-2026-59821

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to creat...

CVE-2026-59821 LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to creat...

CVE-2026-59821 LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to creat...

CVE-2026-59821 LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to creat...

CVE-2026-15044

A flaw was found in the TrustyAI Service Operator. When deploying services like gorch or NemoGuardrails, if a specific security setting is not enabled, these services can expose their communication channels without requiring users to prove their identity. This allows any other program within the...

CVE-2026-15044

A flaw was found in the TrustyAI Service Operator. When deploying services like gorch or NemoGuardrails, if a specific security setting is not enabled, these services can expose their communication channels without requiring users to prove their identity. This allows any other program within the...

CVE-2026-15044 Trustyai-service-operator: trustyai service operator: unauthenticated access to ai guardrails and orchestrator apis

A flaw was found in the TrustyAI Service Operator. When deploying services like gorch or NemoGuardrails, if a specific security setting is not enabled, these services can expose their communication channels without requiring users to prove their identity. This allows any other program within the...

EUVD-2026-42283

A flaw was found in the TrustyAI Service Operator. When deploying services like gorch or NemoGuardrails, if a specific security setting is not enabled, these services can expose their communication channels without requiring users to prove their identity. This allows any other program within the...

CVE-2026-15044 Trustyai-service-operator: trustyai service operator: unauthenticated access to ai guardrails and orchestrator apis

A flaw was found in the TrustyAI Service Operator. When deploying services like gorch or NemoGuardrails, if a specific security setting is not enabled, these services can expose their communication channels without requiring users to prove their identity. This allows any other program within the...

CVE-2026-15044

The CVE concerns the TrustyAI Service Operator. In deployments of services such as gorch and NemoGuardrails, if a specific security setting is not enabled, communication channels can be exposed without requiring user authentication, allowing any other program in the cluster to access the AI guard...