IAGA-Sentinel v1.9.2

IAGA Sentinel The EU AI Act conformity evidence layer for AI agents. Cryptographically signed, replay-verifiable evidence of every action an agent routes through it, structured to support AI Act Article 12 record-keeping and Annex IV documentation. Documentation · Quickstart · Autonomous agent...

CVE-2026-61951

creationtimestamp| type| source ---|---|--- 2026-07-23 13:08:06+00:00| seen| https://bsky.app/profile/stackflag.bsky.social/post/3mrcvta62f32r...

ToolGuardian: Declarative Security for AI Agent-Tool Interactions

LLM agents increasingly rely on external tools, expanding capability while creating a new security boundary: third-party tools may appear benign at the interface level while embedding unsafe behavior in implementation. Existing defenses rely on weak metadata, collapse characterization and policy...

Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis

Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language models LLMs demonstrate impressive capabilities for technical artifact interpretation, the opacity and escalating API costs of closed-weight...

CVE-2026-60292

creationtimestamp| type| source ---|---|--- 2026-07-21 23:48:07+00:00| seen| https://bsky.app/profile/stackflag.bsky.social/post/3mr6ynsyrfe2v 2026-07-23 16:50:59+00:00| seen| https://www.acn.gov.it/portale/w/critical-patch-update-di-oracle-9 2026-07-29 17:07:07+00:00| seen|...

Epoch-BreachScope

🛡️ BreachScope Hermes BreachScope Hermes is an agentic AI...

EUVD-2026-46251

Memory safety bugs present in Firefox ESR 115.37, Firefox ESR 140.12 and Firefox 152. Some of these bugs showed evidence of memory corruption and we presume that with enough effort some of these could have been exploited to run arbitrary code. This vulnerability was fixed in Firefox 153, Firefox...

nebula v2.0.1b2

Nebula AI Powered Pentesting The Zero Layer workbench Acknowledgement First, I would like to thank Almighty God, who is the source of all knowledge. Without Him, this would not be possible. Nebula brings the working parts of a security engagement into one desktop surface: terminal, code, browser,...

SecureAI-Scan v0.4.0

SecureAI-Scan The AI security scanner that proves its findings. SecureAI-Scan finds LLM, MCP, Agent Skill, and RAG vulnerabilities in TypeScript, JavaScript, and Python — and shows you the evidence: the exact source → flow → sink path for every dataflow finding, resolved through real imports, not...

CARE: Pre-Execution Command Verification for Shell-Executing LLM Agents

Large Language Model LLM agents are increasingly used for coding and terminal automation, making shell-command dispatch a high-stakes runtime control point. We study command-level pre-execution mediation for individual shell commands produced by LLM agents under bounded path context. Existing...

When to Trust the Map: Confidence-Aware LLM Routing for Automotive CVE-To-ATM Mapping

Public CVE descriptions report the technical conditions and impact of vulnerabilities, whereas the Auto-ISAC Automotive Threat Matrix ATM expresses an adversary's tactics and techniques. Because the two representations are not directly aligned, incorrect automated mappings in safety-critical...

Top Five Compliance Audit Software and Tools: Mastering Modern Regulatory Risk

Executive Summary Manual audit preparation no longer scales across hybrid, cloud, endpoint, and application environments. Compliance monitoring software must move from checklist validation to continuous control monitoring. The strongest platforms connect evidence collection with risk...

A Non-Intrusive Traffic Analysis Framework for Authorization Risk Detection and Coordinated Response in Web Applications

Authorization violations under valid Web sessions are difficult to identify and handle in real time from traffic because they depend strongly on business semantics and exhibit few distinctive protocol-level features. This paper proposes a non-intrusive traffic analysis framework for authorization...

CVE-2022-25476

creationtimestamp| type| source ---|---|--- 2026-07-16 19:00:04+00:00| seen| Telegram/lkTqxrRLFzmZiKWrqHB7ywSYEM6i5xRhttz45dAnhSWBug 2026-07-16 19:00:04+00:00| seen| Telegram/5kmF1XOjEGp2eusQzn0DreB4leSvC4mbJ6rdQEpWsm7WOU 2026-07-17 00:00:26+00:00| published-proof-of-concept|...

CVE-2026-58078

creationtimestamp| type| source ---|---|--- 2026-07-16 10:56:44+00:00| seen| https://bsky.app/profile/cve.skyfleet.blue/post/3mqr37ucybl2s...

AI Can Find Bugs, But Human Knowledge Still Proves Them

Artificial intelligence AI is changing offensive security, but it has not changed the standard that matters most: a finding has to be proven before it becomes useful. AI-assisted tools can read code quickly, generate payloads, summarize attack surfaces, explain unfamiliar APIs, and run repetitive...

FlowGuard: From Signals to Evidence for MCP Security Detection

The Model Context Protocol MCP enables LLM agents to interact with external tools through metadata exchange, tool invocation, and response consumption. Existing MCP security scanners primarily reason about suspicious semantic signals rather than real execution behaviors, which can lead to...

How Pentera Turns AI Security Workflows into Validation Engines

AI security agents are starting to influence real security decisions. They summarize findings, prioritize remediation, recommend next steps, and help teams move faster. But most still rely on fragmented risk signals: scanner output, severity scores, threat intelligence, configuration findings, an...

When Binaries Talk Back: Representation-Confusion Attacks on LLM-Assisted Reverse Engineering

LLM-assisted reverse-engineering RE systems analyze strings, decompiler output, and tool reports derived from ttacker-controlled binaries. A binary can make data look like instructions or records from one origin look like independent evidence. We call such failures Representation-Confusion Attack...

MAL-2026-10191 Malicious code in data-harvester (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 21c2e2c21d9afac9277d95589962d33a09651a5b6ef7e0b3c9e07aee56af213f On first import, dataharvester/init.py decodes a base64-embedded 486KB Linux ELF, writes it to /.config/.npm-cache/snapd-network, sets mode 0777, and...