oss-fuzz-gen

Un framework per la generazione e la valutazione di fuzz target Questo framework genera fuzz target per progetti reali C/C++/Java/Python con vari Large Language Models LLM e li valuta tramite la piattaforma OSS-Fuzz. Maggiori dettagli disponibili in AI-Powered Fuzzing: Breaking the Bug Hunting...

kong

Kong: Il Reverse Engineer Agentico Orchestrazione LLM per il reverse engineering di binari Cos'è Kong? La maggior parte delle attività segue una relazione lineare: più un compito è difficile, più tempo richiede solitamente. Il reverse engineering e l'analisi binaria è un'attività in cui la...

markdown-exfil-tester

valtik-markdown-exfil-tester Tester black-box per iniezione indiretta di prompt che porta all'esfiltrazione di markdown / HTML in chatbot basati su LLM. Questa è la classe di vulnerabilità che ha colpito Microsoft 365 Copilot CVE-2025-32711, aka EchoLeak, ChatGPT patch OpenAI Febbraio 2026 e...

inspect_petri

Inspect Petri Benvenuto in Inspect Petri, un agente di auditing che permette il monitoraggio automatizzato e l'interazione con modelli linguistici per rilevare potenziali problemi di allineamento, reward hacking e altri comportamenti preoccupanti. Petri ti aiuta a testare rapidamente ipotesi di...

www-project-top-10-for-large-language-model-applications

www-project-top-10-for-large-language-model-applications Repository Web della Fondazione OWASP OWASP Top 10 per le Applicazioni dei Grandi Modelli Linguistici...

EntropicaPublic

Aggiornamenti di marzo Devo spostare qui parte del lavoro dai repository privati. Continua l'esplorazione dell'uso di modelli massicciamente multi-testa con funzioni mixer e readout separate. Attualmente sto addestrando una TinyStories in cinese su un modello equivalente a 3B che si addestra...

CVE-2026-72742

DSPy 3.3.0b1 contains a file exfiltration vulnerability in the Image and Audio output field adapters that allows attackers with influence over language model outputs to read arbitrary local files by injecting a filesystem path into the url field of a parsed Image or Audio typed output. The...

EUVD-2026-56886

DSPy 3.3.0b1 contains a file exfiltration vulnerability in the Image and Audio output field adapters that allows attackers with influence over language model outputs to read arbitrary local files by injecting a filesystem path into the url field of a parsed Image or Audio typed output. The...

PT-2026-70872

DSPy 3.3.0b1 contains a file exfiltration vulnerability in the Image and Audio output field adapters that allows attackers with influence over language model outputs to read arbitrary local files by injecting a filesystem path into the url field of a parsed Image or Audio typed output. The...

CVE-2026-9196

IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components. The application executes model‑generated Python code in the backend during validation prior to user...

MalTotal: Cost-Effective and Language-Agnostic Malicious Code Poisoning Detection for Millions of Repositories

The widespread adoption of open source software OSS has introduced significant security risks, with malicious code poisoning attacks increasingly targeting public package registries and open-source platforms. Existing detection approaches, including heuristic-, learning-, and LLM-based methods,...

CVE-2026-67598

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-2026-52405

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...

CVE-2026-65699

AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user's agent run by supplying a target runid in the request body without ownership verification. The AgentCRUD.createtask and...

CVE-2026-65699

AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user's agent run by supplying a target runid in the request body without ownership verification. The AgentCRUD.createtask and...

PYSEC-2026-3498 PocketSphinx: Buffer overflows in language and acoustic model loading code

Impact The trie language model code introduced in PocketSphinx 5prealpha failed to check various boundary conditions when reading the headers of ARPA, DMP, and binary format language model files. In the case of invalid, corrupted or malicious input files, this could lead to stack and heap buffer...

n8n: Custom Header Credential Values Leaked in Plaintext into LLM Node Execution Data

Impact Custom HTTP headers configured in credentials for certain LLM sub-nodes including OpenAI, Anthropic, and Lemonade are masked in the n8n UI but are written in plaintext into execution data during workflow runs. Any authenticated user with access to the execution data for an affected workflo...

GHSA-89GH-3PGC-V5H2 n8n: Custom Header Credential Values Leaked in Plaintext into LLM Node Execution Data

Impact Custom HTTP headers configured in credentials for certain LLM sub-nodes including OpenAI, Anthropic, and Lemonade are masked in the n8n UI but are written in plaintext into execution data during workflow runs. Any authenticated user with access to the execution data for an affected workflo...

NPM: n8n: Custom Header Credential Values Leaked in Plaintext into LLM Node Execution Data

NPM: n8n: Custom Header Credential Values Leaked in Plaintext into LLM Node Execution Data vulnerability discovered by ? in WordPress Npm n8n versions 1.123.64...

GHSA-FMVG-VHQQ-R2MJ Duplicate Advisory: Custom Header Credential Values Leaked in Plaintext into LLM Node Execution Data

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-89gh-3pgc-v5h2. This link is maintained to preserve external references. Original Description n8n versions before 1.123.64 fail to properly mask custom HTTP header credentials in LLM sub-node execution data,...