Loading story…
Recent advancements in AI-driven penetration testing have led to the development and deployment of tools that can autonomously discover and exploit vulnerabilities in web applications. One such tool, Shannon, leverages Anthropic’s Claude Agent SDK to perform comprehensive white-box analysis, autonomously identifying attack paths and executing real browser-based exploits. Shannon has demonstrated performance surpassing human pentesters on industry benchmarks, providing detailed, low-noise reports and simulating the workflows of experienced security engineers.
In parallel, practitioners are exploring orchestration techniques to integrate AI models and penetration testing frameworks across different environments. A practical setup involves running large language models on an Ubuntu host and orchestrating the HexStrike penetration testing tool on a Kali Linux virtual machine, bridged via SSH. This configuration enables local AI models to automate and drive penetration testing tasks, with considerations for model performance and the potential need to scale to GPU or cloud-based solutions for more demanding scenarios.
Get the actors, campaigns, and ATT&CK mapping behind it.
2 events from the most recent confirmed update back to the earliest known activity.
A practical guide details how to integrate HexStrike MCP orchestration with Ollama using an Ubuntu host and a Kali Linux VM connected over SSH. The write-up notes successful use of models such as Qwen3 8B and 14B and highlights performance limits that may require GPU or cloud-hosted models.
A report describes Shannon, an autonomous AI-powered web application and API penetration testing tool built on Anthropic’s Claude Agent SDK. It is presented as outperforming human pentesters and other proprietary AI systems on the XBOW benchmark while focusing on proving real exploitable vulnerabilities.
Get the adversaries, campaigns, and ATT&CK mapping behind this technique, with detections ready to deploy.
2 references tracked. Mallory keeps watching after this page renders.
Map indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Two new **AI-assisted offensive security** efforts were highlighted: *BlacksmithAI*, an open-source penetration testing framework, and a **Kali Linux** workflow that enables natural-language control of common pentesting tools via Anthropic’s **Claude**. BlacksmithAI is described as a hierarchical, multi-agent system where an orchestrator decomposes assessment goals and delegates work to specialized agents aligned to typical pentest phases (recon, scanning/enumeration, vulnerability analysis, exploitation, and post-exploitation), then compiles results into reporting. Separately, Kali Linux was reported to support a native AI-assisted workflow by integrating Claude through the open-source **Model Context Protocol (MCP)**, using an `mcp-kali-server` package to translate plain-English prompts into tool execution (e.g., Nmap/Gobuster/Metasploit), parse outputs, and return structured findings and prioritized reporting. Both items reflect a broader shift toward **agentic and conversational interfaces** for offensive tooling, reducing reliance on manual CLI syntax while automating planning, execution, and summarization of assessment steps.
Jun 29, 2026
Threat actors are increasingly leveraging artificial intelligence, particularly large language models (LLMs), to automate and enhance cyberattacks. Recent research demonstrates that LLMs such as GPT-4o and Claude can be manipulated to generate working exploits for enterprise software like Odoo ERP, significantly lowering the barrier for less-skilled attackers to launch sophisticated attacks. Concurrently, the underground market is witnessing the emergence of AI-powered malware tools, such as metamorphic crypters, which use AI to dynamically rewrite malicious code and evade detection by endpoint security solutions like Windows Defender. These developments highlight a rapidly evolving threat landscape where AI is both a tool for attackers and a challenge for defenders. In response to these threats, the cybersecurity community is developing advanced AI-powered penetration testing frameworks like NeuroSploitv2. This tool integrates multiple LLMs and employs specialized agent roles, grounding techniques, and safety guardrails to automate vulnerability discovery and exploitation in a controlled, ethical manner. Meanwhile, defenders are also exploring granular attribute-based access control and post-quantum encryption to mitigate risks from context window injections in AI systems. The convergence of AI in both offensive and defensive security operations underscores the urgent need for robust safeguards and adaptive security strategies to address the dual-use nature of these technologies.
Jun 29, 2026
Security researchers and vendors documented rapid progress in using large language models and autonomous agents for offensive security testing, from early machine-learning-driven exploitation in **Deep Exploit** to newer multi-agent systems such as **BLADE** and Mastra-based workflows. In controlled demonstrations, these systems automated parts of reconnaissance, privilege-escalation analysis, credential discovery, lateral movement, and reporting, while broader evaluations found modern models increasingly capable of code understanding, vulnerability reasoning, and black-box web assessment tasks. The reporting also highlighted industry milestones such as AI-assisted pentesting tools reaching top bug bounty rankings and the growing use of agent patterns including **ReAct**, **Plan-and-Execute**, and orchestrated multi-agent designs for security assessments. At the same time, the same body of work warned that AI-for-security deployments are creating new attack surfaces. Researchers observed internet scanning for exposed OpenAI-compatible `Chat Completions` endpoints, with likely goals including fingerprinting LLM servers, abusing unauthenticated inference, causing denial of service, and reaching downstream integrations such as **RAG**, tool calling, and URL fetching. Separate analysis warned that long-term memory in AI agents can preserve attacker-influenced instructions, stale conclusions, or misleading context across sessions, making provenance, freshness, access control, correction, and deletion critical controls. Across the studies, the message was consistent: AI agents are becoming more useful for security operations and testing, but their deployment requires strict governance, authentication, and safeguards against prompt injection, unstable execution, and low-quality automated findings.
Aug 15, 2026