paseo-poc-repo-trust

paseo-poc-repo-trust — DEMO PoC repository ⚠️ This is a sec...

MutMem: Cryptographically Authorized Mutation in Persistent Agent Memory

Persistent agent memory must adapt as later outcomes change earlier evidence, yet mutable retrieval weights create an attribution problem: reviewers must distinguish authorized adaptation from database tampering. We present MutMem, an authorized-mutation protocol in HOM-AIMOS, a persistent...

RFE Standards

Minimum Viable Standard MVS & Request for Evidence RFE Framework - Decompose bloated, legacy RFCs X.509/ASN.1 and RFC 3986 URIs into usage-driven, empirical standards. Coverage is dictated by observable real-world usage data plus an explicit Criticality Override Registry - not design-by-committee...

spar

SPAR backend Python core: attacker/defender agents, orchestra...

Root-the-Box

EH-Stage6: Exploit Chain as Code This repository contains my...

Exploit for CVE-2026-66066

rails-activestorage-vips-audit An Agent Skillhttps://agent...

Operationalize AI Governance Across Shadow GenAI, MCP, and Agentic Workloads with Qualys TotalAI

Key Takeaways AI adoption has outpaced enterprise controls, with AI and LLM workloads appearing faster than security teams can inventory or approve them. AI governance has become an evidence problem. Policies, questionnaires, and risk registers cannot prove that AI systems are safe. Traditional...

Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detection

Real-world vulnerabilities often span multiple functions, yet most learning-based detectors classify each function in isolation: on a sample of real CVEs, we find that 71.7% of vulnerable functions require evidence from outside the function to be classified correctly. Agentic reinforcement learni...

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term memory, recalled much later, and quietly shape a real action. Recent benchmarks increasing...

AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents

Large language model LLM agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools. This dependence allows defenders to inject deceptive observations that can mislead the agent's decision-making process. However, existing...

defenseclaw v0.8.9

root@kitploit: / \ / / / || | / / / / / / /// \ / \ / |/ | | | |/ |\ \ /\ / / / // / / / // /| | | |\ \ /| | | | | | \ V V / // // / || |||/| |||,| // DefenseClaw Security governance for OpenClaw and agentic AI runtimes. Scan capabilities before use, inspect runtime traffic, and export...

vuln-verify

vuln-verify A vulnerability verification engine driven by evi...

(EC)2: Event-Centric Explainability for Cybersecurity through Multi-Agent LLM Investigations

Security operations centers rely on anomaly detection systems to flag suspicious events. Feature-level explanations for anomaly detectors offer limited value for operational investigations. To effectively handle alerts, analysts need to know contextual relationships and need actionable...

Sextortion scammers are exploiting ShinyHunters data leaks

Sextortion scammers are using email addresses from data leaked by the ShinyHunters hacking group to add some credibility to their feeble attempts to convince people they have embarrassing information about them. Sextortion emails are messages claiming that the scammer recorded you through your...

Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation

Cloud telemetry arrives at a scale that, paradoxically, makes intrusion understanding harder rather than easier. Attackers operate through legitimate identity, federated session tokens, and cloud native APIs indistinguishable from routine administration, and analysts spend an incident...

Beyond GDPR: Examining Disclosure Gaps in Mobile AR Privacy Policies under U.S. State Privacy Laws

Mobile Augmented Reality MAR apps can collect and process highly sensitive data such as spatial maps and biometrics, yet their privacy policies remain largely understudied. Prior audits of app privacy policies have typically focused on a single legal framework, such as the GDPR. Meanwhile, 20 U.S...

DeepFaith: Evidence-Grounded LLMs for Faithful Incident Reporting in Multi-Stage APT Defense

Advanced Persistent Threats APTs are difficult to detect and interpret due to their multi-stage and stealthy nature. While recent autonomous defense systems leverage provenance graphs and learning-based models for detection and mitigation, their outputs remain largely machine-oriented and difficu...

IAGA-Sentinel v2.0.0

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...

From Signals to Behaviors: Evidence-Based Android Malware Detection

Android malware remains a persistent threat, and detecting it accurately is a long-standing open problem. Whether an app is malicious depends on what it actually does and the context in which it does it, not on the surface signals it happens to exhibit. Existing detectors instead reason about...

ONNX: Heap-Buffer-Overflow READ in Gemm Version Converter Adapter via Undersized Input Shape

Summary Heap-buffer-overflow READ 16 bytes in Gemm76::adaptgemm76 onnx/versionconverter/adapters/gemm76.h:41 when ConvertVersion processes a model with a Gemm node whose input tensors have fewer than 2 dimensions. The adapter accesses Bshape1 without checking rank. On Release builds the OOB read ...