scopeblind-gateway

protect-mcp Gate di policy Cedar a blocco di default con ricevute firmate per chiamate di strumenti di agenti AI. protect-mcp è un gate che si posiziona davanti alle chiamate di strumenti di un agente AI. Valuta ogni chiamata rispetto a una policy Cedar lo stesso linguaggio che AWS utilizza per...

MakerChecker

🛡️ MakerChecker Il layer di sicurezza open-source per agenti AI. Rifiuto per impostazione predefinita, approvazioni umane e una traccia di audit firmata crittograficamente — così il tuo agente esegue solo ciò che gli è stato concesso e non può provabilmente approvare il proprio lavoro. Sito Web ·...

node9-proxy

🛡️ Node9 Cosa ha fatto davvero il tuo agente AI? Scoprilo. Node9 si posiziona tra il tuo agente AI e gli strumenti che può usare — scopri cosa ha già fatto, proteggiti dalle azioni rischiose in tempo reale e rivedi cosa è successo in qualsiasi finestra temporale. Funziona con Claude Code · Codex...

sage

Sage Sicurezza per gli Agenti — Rilevamento e Risposta per assistenti di codifica AI Sage è un leggero strato di sicurezza che protegge gli agenti AI dall'esecuzione di azioni pericolose. Intercetta le chiamate degli strumenti — comandi shell, recupero URL, scritture di file — e le verifica...

nah

gli errori costosi si fermano qui verdetti in microsecondi. niente LLM. estensibile. nahguard.ai • cosa blocca • come decide • installazione • estensione • modello di minaccia root@kitploit: curl -fsSL nahguard.ai/install | sh claude code · codex · cursor · pi · + altri 10 nah è una guardia che s...

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-2026-37147

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...

GHSA-68XW-R643-9P5W 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 PraisonAI AgentLoop onToolCall approval runs after tool execution

Summary The published npm package praisonai exports createAgentLoop, whose onToolCall callback is documented and exampled as an approval hook. The implementation calls PraisonAI's generateText wrapper with the caller's executable tools first, receives toolResults, and only then calls onToolCall...

GHSA-R7VV-6763-M739 Duplicate Advisory: Skill-command dispatch could skip before-tool-call hooks

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-68xw-r643-9p5w. This link is maintained to preserve external references. Original Description OpenClaw before 2026.5.6 contains a hook bypass vulnerability where skill commands routed through the affected dispat...

Duplicate Advisory: Skill-command dispatch could skip before-tool-call hooks

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-68xw-r643-9p5w. This link is maintained to preserve external references. Original Description OpenClaw before 2026.5.6 contains a hook bypass vulnerability where skill commands routed through the affected dispat...

CVE-2026-53845 OpenClaw < 2026.5.6 - Skill-Command Dispatch Hook Bypass via Before-Tool-Call Hook Skipping

OpenClaw before 2026.5.6 contains a hook bypass vulnerability where skill commands routed through the affected dispatch path skip before-tool-call hook coverage. Attackers can exploit this by sending skill commands through the vulnerable dispatch path to bypass hook-based auditing and policy...