claude-code-guardrails

We have since built a dedicated product to help developers manage AI permissions better, which we intend to make open source. Check it out atstoplight.ai. Claude Code Guardrails settings.json works if: You're fine editing JSON and killing Claude Code sessions every time policy changes Your securi...

tealtiger

TealTiger AI Agent Security & Governance SDK Deterministic governance, guardrails, cost tracking, and policy management for LLM applications. Open source. TypeScript + Python. Works with any provider...

Guardrails

NVIDIA NeMo Guardrails Library LATEST RELEASE / DEVELOPMENT VERSION : The develop branch tracks the latest top of tree development. The latest released version is 0.24.1. ✨✨✨ 📌 The official NeMo Guardrails library documentation is available atdocs.nvidia.com/nemo/guardrails. ✨✨✨ NVIDIA NeMo...

LiteLLM < 1.25.0 - Remote Code Execution

LiteLLM before 1.25.0 allows authenticated users with the master API key to execute arbitrary Python code through the /guardrails/testcustomcode endpoint intended for custom guardrail testing. The endpoint’s insufficient filtering mechanisms can be bypassed, allowing attackers to abuse Python’s...

EUVD-2026-68443

@hulumi/policies versions before 1.3.2 contain an evidence validation bypass vulnerability in Cloudflare and deployment-governance validators that allows attackers to suppress violations by submitting unrelated compliant evidence. Attackers can use evidence from different zones, hostnames, origin...

CVE-2026-82855 @hulumi/policies before 1.3.2 Evidence Validation Bypass

@hulumi/policies versions before 1.3.2 contain an evidence validation bypass vulnerability in Cloudflare and deployment-governance validators that allows attackers to suppress violations by submitting unrelated compliant evidence. Attackers can use evidence from different zones, hostnames, origin...

CVE-2026-82855: Protection Mechanism Failure

@hulumi/policies versions before 1.3.2 contain an evidence validation bypass vulnerability in Cloudflare and deployment-governance validators that allows attackers to suppress violations by submitting unrelated compliant evidence. Attackers can use evidence from different zones, hostnames, origin...

GHSA-J659-8XH6-5PQ5 atomic-agents-stack: Parallel helper/delegate batch reserves $0 for models absent from the pricing table, bypassing the cost-cap fan-out guard

estimatebatchcost atomicagents/agent.py looks up the per-model output price with PRICING.getmodel, , returning 0.0 for any model not in the hardcoded pricing table. checkbatchreservation then early-returns when the reservation is 0 and that an over-cap unknown-model batch raises...

“I’m Allowed”: Hackers Use Simple Claims to Bypass AI Guardrails

Cisco Talos found hackers using simple authorization claims to bypass AI guardrails, build DDoS attack tools, steal credentials and access live camera services...

MCP Server Security: The Blind Spot in Your AI Stack

Short version: an MCP server is the tooling layer that lets an AI agent act on external systems. Hosted remotely, it is an API endpoint like any other — and it needs bot and WAF controls in front of it, API security on its own endpoints, and AI guardrails that inspect what the tools send back, no...

VulnCheck KEV: CVE-2026-40217

LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/testcustomcode URI...

VulnCheck KEV: 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...

Code Injection

LiteLLM is vulnerable to Code Injection. The vulnerability is due to insufficient sandboxing and validation of custom Python code submitted through the Custom Code Guardrails create and update paths, which allows a privileged attacker with guardrail management access to execute arbitrary Python...

LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks

ImpactLiteLLM's Custom Code Guardrails production create/update paths did not apply the same sandboxing and validation used by the test endpoint.A privileged user with access to create or update guardrails could submit custom Python code that executed in the LiteLLM proxy environment. In...

PYSEC-2026-3478 LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks

Impact LiteLLM's Custom Code Guardrails production create/update paths did not apply the same sandboxing and validation used by the test endpoint. A privileged user with access to create or update guardrails could submit custom Python code that executed in the LiteLLM proxy environment. In...

PT-2026-64088

Impact LiteLLM's Custom Code Guardrails production create/update paths did not apply the same sandboxing and validation used by the test endpoint. A privileged user with access to create or update guardrails could submit custom Python code that executed in the LiteLLM proxy environment. In...

LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks

Impact LiteLLM's Custom Code Guardrails production create/update paths did not apply the same sandboxing and validation used by the test endpoint. A privileged user with access to create or update guardrails could submit custom Python code that executed in the LiteLLM proxy environment. In...

GHSA-72M8-9M7M-H278 LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks

Impact LiteLLM's Custom Code Guardrails production create/update paths did not apply the same sandboxing and validation used by the test endpoint. A privileged user with access to create or update guardrails could submit custom Python code that executed in the LiteLLM proxy environment. In...

EUVD-2026-42350

LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks...

CVE-2026-56349

n8n before version 2.10.0 contains an input validation vulnerability in the Guardrail node that allows attackers to bypass default guardrail instructions. End users can craft malicious inputs to circumvent guardrail protections and compromise workflow integrity...