49 matches found
seclab-taskflow-agent
GitHub Security Lab Taskflow Agent The Security Lab Taskflow Agent is an MCP-enabled multi-Agent framework for declarative, YAML-driven agentic workflows. Built on top of the OpenAI Agents SDK, it uses Pydantic for grammar validation and Jinja2 for template rendering. Core Concepts The Taskflow...
Attackers Compromise Microsoft's Agent Framework PyPI Package to Steal Cloud Credentials
Threat actors have compromised Microsoft's agent-framework package to push a credential stealer, according to reports from Aikido, Chainguard, Endor Labs, OX Security, SafeDep, Socket, StepSecurity, and Google-owned Wiz. The malicious versions, 1.26.1 and 1.26.2, were published 33 minutes apart o...
Malicious code in agent-framework (PyPI)
Malicious releases of the legitimate "agent-framework" package Microsoft Agent Framework. Versions 1.26.1 and 1.26.2 add a credential stealer that is not present in the last clean release, 1.26.0. Both releases were published on 2026-11-17 1.26.1 at 20:35 UTC as a wheel only, 1.26.2 at 21:08 UTC...
CVE-2025-68664
CVE-2025-68664 All I Want for Christmas Is Your Secrets: LangGrinch Strikes LangChain Core CVE-2025-68664 Author: Yarden Porat Cyata Research: LangGrinch Vulnerability in LangChain Published: https://cyata.ai/blog/langgrinch-langchain-core-cve-2025-68664/ Yesterday LangChain published a critical...
AWE
AWE: Adaptive Agents for Dynamic Web Penetration Testing Akshat Singh Jaswal · Ashish Baghel Accepted at NDSS LAST-X 2026 Abstract Modern web applications are increasingly produced through AI-assisted development and rapid no-code deployment pipelines, widening the gap between accelerating softwa...
From a Docker Ping to an AI Command Plane: Inside the Hermes Attack Workbench and Carbonato Model Gateway — Part 1: Discovery
Key Takeaways Our research into an attempted Docker takeover shows how exposed Docker APIs can create opportunities for host compromise. The attacker attempted to access the host filesystem and deploy payloads designed for remote access and persistence. We traced these attempts to the attacker’s...
DeepAVR: Deep Analysis Via Multi-Agent Collaboration for Automated Vulnerability Repair
Automated Vulnerability Repair AVR has emerged as a critical defense against software security flaws, aiming to triage and fix bugs autonomously. Early LLM-based approaches focused on patch generation under the assumption of perfect fault localization, while recent end-to-end methods attempt to...
RegoMender: A Multi-Agent Framework for Automated Rego Policy Repair
Policy-as-Code PaC has emerged as a foundational paradigm in cloud-native systems. However, repairing Rego policies remains challenging due to their strict syntax, declarative semantics, and specific verification requirements. Existing automated program repair APR methods are mainly designed for...
HydraPoT: A Configurable Multi-Agent Framework for Cost-Aware LLM-Assisted Honeypots
Large language models LLMs can improve honeypot realism by generating dynamic, context-aware responses, but powerful cloud models incur substantial cost and latency, while lightweight models may provide weaker deception. This forces practitioners to choose between operational efficiency and...
CLEANSTART-2026-QG98494 Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
Security vulnerability affects the py3-pydantic-ai package. Pydantic AI is a Python agent framework for building applications and workflows with Generative AI...
CLEANSTART-2026-EE95279 Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
Security vulnerability affects the py3-pydantic-ai package. Pydantic AI is a Python agent framework for building applications and workflows with Generative AI...
CLEANSTART-2026-BF25173 Pydantic AI is a Python agent framework for building applications and workflows with Generative AI
Security vulnerability affects the py3-pydantic-ai package. Pydantic AI is a Python agent framework for building applications and workflows with Generative AI...
EviRepair: Evidence-Driven Agents for Reliable Vulnerability Repair
Recent advances in large language models LLMs have enabled agent-based approaches for repository-level automated vulnerability repair AVR, showing promising repair capabilities. However, an important issue has received limited attention: how can we ensure that the evidence generated during the...
From Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage
Security operations centers SOCs must triage large volumes of alerts, most of which are benign, while missed attacks can remain uninvestigated. Tool-using large language model LLM agents can retrieve evidence during triage, but it remains unclear how reasoning strategies determine what to gather...
One Pipeline Does Not Fit All: TAILOR, a Type- and State-Aware Framework for CVE Reproduction
Growing vulnerability disclosure and widespread software reuse increase security teams' need for reproducible evidence to diagnose vulnerabilities, validate patches, and build regression tests. Producing such evidence at scale requires automated end-to-end CVE reproduction. Existing methods...
SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection
Real-time payment fraud detection is a non-stationary streaming prediction problem: adversaries adapt before supervised labels mature, and localized burst attacks can cause losses before retraining. Production systems typically rely on tabular classifiers and rules, which can struggle to capture...
Autonomous AI Agents Compromise Thousands of Credentials in Under Six Hours
Threat actors are continuing to leverage artificial intelligence AI to streamline their operations, with one financially motivated hacking group employing an autonomous, multi-agent attack framework to carry out a large-scale credential harvesting campaign within six hours. Google Threat...
Malicious code in agent-framework-web (npm)
Source: amazon-inspector fc8c54e8fb3b687786f6141ea8ea92fa6eeb60de018eb8543a325bac6eed1f67 The package agent-framework-web was found to contain malicious code. --- Credit: OpenSSF source...
CVE-2026-62674 Omnigent: Shared Agent Bundle Overwrite Leads to Authenticated Runner RCE
Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, PUT /sessions/sessionid/agent checks LEVELEDIT permission for a session but does not reject a bound shared or template agent whose agent.sessionid is None. An authenticated user with ed...
Defending Retrieval-Augmented Intrusion Detection against Knowledge Poisoning and Prompt Injection
Retrieval-Augmented Generation RAG enables large language models to classify network flows and generate human-readable incident reports by retrieving semantically similar historical traffic from a vector knowledge base. However, the retrieval layer introduces vulnerabilities to knowledge poisonin...