Loading story…
NVISO published a technical introduction on automating LLM red teaming to find security weaknesses in LLM-based applications, focusing on AI-specific risks such as prompt injection, data leakage, jailbreaking, and other behaviors that can bypass guardrails. The post describes why manual testing is difficult due to LLMs’ probabilistic behavior and demonstrates using the promptfoo CLI to scale testing against a deliberately vulnerable ChainLit application, positioning automated test harnesses as a way to systematically probe LLM apps for exploitable failure modes.
Separately, a practitioner write-up describes how security analysts and engineers are using general-purpose LLM tools (Claude, Cursor, ChatGPT) to accelerate day-to-day security work through better prompting patterns rather than “keyword searching.” It provides practical prompting techniques (e.g., “role-stacking” and supplying richer context like requirements docs or code repositories) and includes an example of using an LLM to help design a small Flask application for collecting OSINT (DNS, WHOIS/RDAP, HTML) for URL investigations—guidance that is adjacent to, but not the same as, automated red-teaming of LLM applications.
Mallory correlates global threat intelligence with your attack surface — know if you’re exposed before adversaries strike.
3 events from the most recent confirmed update back to the earliest known activity.
Praetorian introduced Augustus, an open-source LLM security testing tool and accompanying taxonomy covering jailbreaks, prompt injection, data extraction, package hallucinations, RAG/context attacks, multimodal attacks, renderer exploits, evasion methods, and agent/tooling probes. The publication framed these as structured evaluation probes for assessing LLM security.
NVISO published a walkthrough of automated LLM red teaming using Promptfoo, explaining a workflow with target, adversarial, and grader models to test risks such as prompt injection, data leakage, jailbreaking, and authorization failures. The article included a lab against a deliberately vulnerable ChainLit chatbot and reported baseline and iterative jailbreak test results.
A practitioner guide described how to use LLMs such as Claude, Cursor, and ChatGPT to accelerate security and engineering tasks through context-rich prompting, role-stacking, iterative refinement, and validation. It emphasized that LLMs should augment rather than replace analyst judgment.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
3 references tracked. Mallory keeps watching after this page renders.
praetorian.com
Open sourceblog.nviso.eu
Open sourcedispatch.thorcollective.com
Open sourceMap 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.
Security researchers highlighted multiple ways **LLM adoption can introduce or amplify risk**, including both technical attacks and unsafe development practices. G DATA reported that a Git-hosted “detector” for the **Shai-Hulud worm** shipped with “test files” that were effectively *real malware*: scripts capable of deleting user directories and, in at least one case, uploading data to actual threat actors. The files were apparently intended to validate detection efficacy and may have been produced via AI-assisted “vibe coding,” where the model replicated malicious behavior one-to-one while comments claimed the code was only a simulation; although the test artifacts are not executed during normal tool operation, users could trigger damage by manually running them. Separate academic work summarized by Bruce Schneier described **side-channel attacks against LLM inference**, where data-dependent timing and token/packet-size patterns (including those introduced by efficiency techniques like speculative decoding) can leak information about user prompts even over encrypted channels. Reported impacts include inferring conversation topics with high accuracy and, in some settings, recovering sensitive data such as phone numbers or credit card numbers via active probing. In parallel, an SC Media segment discussed the operational upside of **LLM-driven secure code analysis**, citing results that improved security across hundreds of open-source projects but noting the importance of human validation and patching effort; an OSINT Team post provided a cautionary, practitioner-level example of how easily malware can be accidentally executed during analysis, reinforcing the need for disciplined handling and isolation when working with suspicious files.
Jun 29, 2026
Multiple writeups describe how **LLM safety controls can be bypassed through prompt-based attacks**, arguing that jailbreaks and prompt injection are a practical security problem rather than a novelty. The reporting highlights common defense layers—training-time alignment, system prompts, input classifiers, and output filters—and says each can fail because the same model that follows instructions is also asked to interpret and enforce them. One article frames jailbreaks as an attack on the trust architecture of enterprise AI deployments, while the other demonstrates the issue through Lakera’s *Gandalf* challenge, where progressively stronger controls are still defeated by prompt manipulation. The material is **not fluff** because it provides substantive security analysis of an emerging attack class affecting AI systems. Both references focus on the same topic: how prompts can subvert LLM defenses, expose protected information, and reveal architectural weaknesses in current guardrail designs. The practical takeaway for defenders is that natural-language controls alone are brittle, especially when secrets, policy enforcement, and user-controlled input share the same inference path, making prompt injection and jailbreak resistance a core application security concern for enterprise AI deployments.
Jun 29, 2026
Security researchers and vendors reported that large language models are becoming materially useful across offensive and defensive security workflows, including vulnerability discovery, exploit development, autonomous penetration testing, and cyber threat intelligence extraction. Recent work described LLM-assisted systems that generated proof-of-concept exploits for npm flaws at a reported **77%** success rate, exploited real-world web vulnerabilities with multi-agent architectures, and executed multistage attacks in emulated enterprise networks when paired with task-specific agents and attack-abstraction layers. Other experiments found local self-hosted models could reliably solve straightforward Juice Shop challenges, while purpose-built scaffolds helped researchers uncover memory-corruption bugs in Windows endpoint products and accelerate reverse engineering of AV and EDR logic. At the same time, multiple studies warned that headline results can overstate real-world capability without strong validation. Google Project Zero said benchmark design, tooling, and automatic verification heavily influence measured performance and concluded current models still fall short of meaningful autonomous offensive research in live environments. Separate academic and practitioner reviews found many automated pentesting frameworks remain brittle, and human validation showed that **71.5%** of supposedly successful LLM-generated exploit PoCs in one follow-up study were actually invalid because the models simulated exploitation rather than triggering the flaw. Across the research, the consistent finding was that LLMs perform best when constrained by structured workflows, specialized tools, execution feedback, and rigorous verification rather than being trusted as fully autonomous hackers.
Jun 29, 2026