nah

expensive mistakes stop here a guard that blocks catastrophic agent actions nahguard.ai • what it blocks • how it decides • install • extend • threat model claude code · codex · cursor · pi · + 11 more nah is a guard that sits in your coding agent's hook path and reads tool calls before they run...

MakerChecker

🛡️ MakerChecker The open-source security layer for AI agents. Deny-by-default enforcement, human approvals, and a cryptographically signed audit trail — so your agent runs only what it's granted and provably can't approve its own work. Website · Live Demo · mc scan · Docs...

sage

Sage Safety for Agents — Agent Detection & Response for AI coding assistants Sage is a lightweight security layer that protects AI agents from executing dangerous actions. It intercepts tool calls — shell commands, URL fetches, file writes — and checks them against multiple threat detection layer...

node9-proxy

🛡️ node9 IAM for your AI agents Your AI agents can reach Slack, GitHub, email, and your database. node9 decides what they may do with each one...

scopeblind-gateway

protect-mcp Fail-closed Cedar policy gate plus signed receipts for AI agent tool calls. protect-mcp is a gate that sits in front of an AI agent's tool calls. It evaluates each call against a Cedar policy the same language AWS uses for IAM, blocks what breaks the rules before it runs, and signs an...

ROPE

ROPE: Routed Origin Policy Enforcement Source code of our paper: ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection by Xinhang Ma, Chaowei Xiao, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik Abstract Indirect prompt injection IPI plants instructions in the content a...

CVE-2026-78230

AshAi exposes Ash read actions to language-model tool calls. The read tool accepts an aggregate result type min, max, sum, avg that builds an ad-hoc Ash.Query.Aggregate over a named field and returns its raw value. Ash field policies redact forbidden fields on returned records replacing them with...

CVE-2026-82579 AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service

Loop with Unreachable Exit Condition Infinite Loop vulnerability in ash-project ashai allows an attacker who can influence a model's output to hang the tool loop and drive unbounded, repeated model requests. AshAi.ToolLoop classifies a model response of :toolcalls, then filters the calls through...

CVE-2026-55532: Origin Validation Error

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream validateorigin uses requestorigin.startswithallowed, allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests...

Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing

Summary Xinference used Python's unsafe eval function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API, a remote attacker can craft prompts that cause the model to...

CVE-2026-61539 Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing

Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval in xinference/model/llm/toolparsers/llama3toolparser.py and xinference/model/llm/utils.py. Requests to...

CVE-2026-61539

Xinference (an inference API for open-source, speech, and multimodal models) versions 2.5.0 and earlier are vulnerable to remote code execution via unsafe use of Python's eval() in Llama3 tool-call parsing. An unauthenticated remote attacker can craft a prompt sent to /v1/chat/completions with a ...

PT-2026-79457

Name of the Vulnerable Software and Affected Versions Xinference versions prior to 2.7.0 Description Xinference passes attacker-influenced Llama3 tool-call output to the eval function within xinference/model/llm/tool parsers/llama3 tool parser.py and xinference/model/llm/utils.py. Requests sent t...

CVE-2026-54689

creationtimestamp| type| source ---|---|--- 2026-08-19 20:35:08+00:00| published-proof-of-concept| https://github.com/ihor-sokoliuk/mcp-searxng/security/advisories/GHSA-wppf-h75h-6pm6...

CVE-2026-65975

A flaw was found in Pydantic AI's UI adapters, specifically within the sanitizemessages function. This vulnerability allows a remote client to bypass security checks and execute server tools with arguments they provide, rather than those generated by the AI model. This occurs when a trailing clie...

EUVD-2026-52405

Emlog Pro through 2.6.23 contains a disabled TLS certificate validation vulnerability in include/service/ai.php that allows network-adjacent attackers to intercept outbound HTTPS requests to configured LLM providers by presenting arbitrary TLS certificates, as CURLOPTSSLVERIFYPEER and...

EUVD-2026-44992

dbt-mcp is a Model Context Protocol server for interacting with dbt. Prior to 1.17.1, DefaultUsageTracker.emittoolcalledevent in src/dbtmcp/tracking/tracking.py serialized every MCP tool call's complete arguments dictionary and sent it through dbtlabsvortex.producer.logproto without redaction,...

EUVD-2026-37147

OpenClaw: Skill-command dispatch could skip before-tool-call hooks...

OpenClaw: Skill-command dispatch could skip before-tool-call hooks

Summary Skill-command dispatch could skip before-tool-call hooks. In affected versions, a skill command routed through the affected dispatch path could run without the same runBeforeToolCallHook coverage as other tool entry points. This advisory is scoped to the named feature and configuration. I...

NPM: OpenClaw: Skill-command dispatch could skip before-tool-call hooks

NPM: OpenClaw: Skill-command dispatch could skip before-tool-call hooks vulnerability discovered by ? in WordPress Npm openclaw versions = 2026.5.5...