security-research

security-research Proof-of-concept code and technical write-ups for vulnerabilities I discovered and reported through coordinated disclosure. Every entry here is already public: the vendor advisory is published and a fixed release is available. Nothing under embargo or in draft is included. The...

cve-2022-30190

cve-2022-30190 Aka Follina = benign POC. Notes: Commit 5ea77 doesn't work...

batch_jailbreak

Official Repo for Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting Kihyun Kim, Hee-Seon Kim, Wonjun Lee, Changick Kim Korea Advanced Institute of Science and Technology KAIST News 2026.09 Our paper has been accepted to AACL-IJCNLP 2026 Main! 🎉 2026.08 Paper is...

EUVD-2026-44637

PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments...

RuleAutoPilot: Synthesizing Deployable Suricata Rules from Network Traffic

Rule-based Intrusion Detection Systems IDS such as Suricata are central to network security, yet crafting effective detection rules demands deep expert knowledge and cannot keep pace with emerging threats. Existing LLM-based approaches can reduce analyst effort, but they either rely on curated...

Malicious code in rand-txs-sdk (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 383599a80e18acfe3bbf819e2c1cc5ec27a4663b2da9e18c7755000857196dc9 The package advertises itself as a random-transaction generator but its exported getTransactions API triggers execution of a hidden code payload...

Benchmarking Cyberattack Detection in Electric Vehicle Charging Infrastructure with Benign User Updates

Cyberattack detection in electric vehicle charging infrastructure is complicated by legitimate post-activation revisions to requested energy and departure time. Charging manipulation attacks can exploit the same interface and variables; therefore, detecting a request change alone does not establi...

MAL-2026-12858 Malicious code in bigops-web-analytics (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 18ba471d08385d30965c87d85316db28f34e4cd5f6f5eb20f5f9cedc33cd12bf On require, index.js loads helpers.js which selects a platform-specific endpoint and fetches an opaque binary payload from string-split-obfuscated...

Adaptive Intrusion Detection System Using Transformer-Based Neural Networks and Continual Learning Approach with Adversarial Investigation

Network intrusion detection systems IDS trained on fixed traffic snapshots decay silently after deployment as threat distributions shift. Fine-tuning models on new attacks triggers catastrophic forgetting, while retraining from scratch is computationally infeasible. Replay-based continual learnin...

Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills

Closed source agent skills may encode proprietary instructions, scripts, constants, and data. Providers may offer their capabilities as services while keeping the underlying packages hidden. Prior work focuses on prompt injection attacks that directly disclose these artifacts, and existing defens...

Cybersecurity Detection Classification with Reasoning-Enabled Language Models

A major issue in Security Operations Centers SOCs is alert fatigue, as the number of detections reported is more than staff can triage in a given day. Prior work prompts or fine-tunes large language models LLMs to emit a triage label directly, but does not train them to reason about whether a...

When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-Offs

Jailbreak defenses are essential for protecting large language models LLMs, but they can also introduce secondary costs that weaken model utility. We present a systematic study of these defense trade-offs along three dimensions: performance impact, over-refusal on benign inputs, and inference cos...

Malicious code in benign-lib (PyPI)

Source: kam193 09477b048d84611002417894ccb3265d246be0156b096a8b47776960d45e9d3d Package hides an executable inside, and starts it when imported. The sandbox analysis shows only starting a calculator, which suggests it's a research attempt without a big harm. --- Category: PROBABLYPENTEST - Packag...

security-research

security-research Proof-of-concept code and technical write-u...

Exploit for CVE-2026-55511

CVE-2026-55511 PoC Non-weaponized proof of concept for a Yamc...

BARS: Benign-Anchored Ranking and Selection for False Alarm Reduction in Network Intrusion Detection

False alarms remain a major barrier to deploying network intrusion detection systems NIDS. In high-volume environments, even a sub-1% false positive rate can generate tens of thousands of daily alerts. Filter-based feature selection is attractive because it operates upstream of the classifier and...

Impact of Benign Connectivity Variations on Intrusion Detection for Encrypted OPC UA Traffic in Industrial Private 5G Networks

Machine learning ML-based intrusion detection systems IDSs are increasingly used to monitor encrypted industrial communication. However, their behavior under realistic private 5G operating conditions remains insufficiently understood. This paper investigates the impact of benign connectivity...

CVE-2026-56074 PraisonAI - Tool Approval Cache Bypass via Coarse-Grained Caching

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent executecommand calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and...

MAL-2026-6127 Malicious code in @onum-releases/utils (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 887866a4734ebf64a639f9d2512cd400085469ec7fa06aba5f1bbe340b2688b8 On require'@onum-releases/utils', index.js reads os.hostname and issues an HTTP GET to 'utils..200majoeu01dk02xnjdajro1isojc90y.oastify.com', leaking...

WordPress Contest Gallery Scanner

This Python script is a assessment tool designed to evaluate potential exposure of a WordPress Contest Gallery AJAX workflow by observing response differences from benign probe requests...