zairo

Measuring zairo zairo's unit tests check that it builds the right prompts and handles answers correctly. They can't tell you whether a model, given those prompts, finds a vulnerability a change introduced, or flags one that isn't there. That's what this directory is for: a set of labelled changes...

OpenAnt

OpenAnt OpenAnt from Knostic is the first open source LLM-based vulnerability discovery and remediation product now called a harness that helps defenders proactively find verified security flaws while minimizing both false positives and false negatives. Stage 1 detects. Stage 2 attacks. What...

resym

ReSym Artifact This repository provides artifacts for the paper "ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries" CCS 2024. 🏆 ACM SIGSAC Distinguished Paper Award Winner Note : We are actively maintaining/updating our artifacts. Please make sure you ar...

Where AI Vulnerability Discovery Harnesses Go Quiet: Structural False Negatives and Hidden Vulnerabilities

LLM-based vulnerability discovery harnesses can miss real, reachable vulnerabilities because of how the harness around the model is built. Steps that select code, filter it, and store and merge findings can drop a vulnerability before or after the model runs, independently of the model's...

MPIDetector: Detecting Multi-Modal Prompt Injection Via LLM-Based Reasoning

With the rapid integration of Multi-modal Large Language Models MLLMs into real-world applications, Prompt Injection PI has emerged as a critical security threat. Attackers can conceal malicious instructions within textual narratives or visual inputs to bypass safety alignment. Existing approache...

stride-gpt

STRIDE GPT è uno strumento di threat modelling basato sull'IA che sfrutta i Large Language Models LLM per generare modelli di minaccia e alberi di attacco per una determinata applicazione basandosi sulla metodologia STRIDE. Gli utenti forniscono i dettagli dell'applicazione, come il tipo di...

Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair

Localizing where an LLM-based agent first fails to uphold security during a repair can show which stage of its workflow needs an additional safeguard. This is difficult for silent failures, which are patches that pass syntactic and functional checks but still contain a security vulnerability...

Beyond Predefined Sinks: Security-Aware Dependency Analysis for LLM Agents

Large language model LLM-based agents increasingly connect model-generated decisions to security-sensitive software capabilities such as command execution, filesystem access, network communication, browser control, and external tools. Existing analyses often use predefined sensitive operations as...

Pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation

Indirect prompt injection embeds malicious instructions within external content retrieved by LLM-based agents, altering target behavior without user authorization. We introduce pikit, a research toolkit designed to systematically evaluate these threats across three core dimensions: attacks 13...

Continuous Assurance of Agentic Security Auditors for Software Delivery Decision Gates

Large language model LLM-based repository auditors are increasingly deployed as security controls within continuous integration CI pipelines, where their findings admit, block, or delay software changes. As Agentic Software Development Life Cycle SDLC Security Controls, their non-deterministic...

CoDeL: Co-Evolutionary Defense against Indirect Prompt Injection in LLM-Based Agents

Large language model LLM-based agents increasingly rely on external tools and content, exposing them to indirect prompt injection IPI. This threat has motivated a wide range of defenses, among which training-based defenses are often regarded as most reliable. However, existing training-based...

ethibench

From Controlled to the Wild: Evaluation of Pentesting Agents in the Real-World AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which systems will perform best on real-world targets. Most existing evaluations...

MetaPermit: Scalable and Auditable Access Control for AI Agents Via LLM-Inferred Meta-Attributes

The rise of autonomous AI agents equipped with tools has introduced significant security risks, ranging from unintended tool misuse to adversarial manipulation through Indirect Prompt Injection IPI attacks. In practice, deployed agent systems such as OpenAI Codex and Claude Code protect tool...

The like Trap: Multi-Stage Poisoning against Agents in Similarity-Based Recommendation Systems

With recent advancements in large language models LLMs and LLM-based agents, these agents are becoming increasingly autonomous and gaining broader access to act on users' behalf on the internet. However, the vulnerability of automated agents deployed on social media platforms e.g., for managing a...

When Verified Source Becomes Attack Input: Defending Smart Contracts against LLM-Based Vulnerability Scanning

Smart contracts are financial programs deployed on blockchains to manage digital assets. To build trust with users and investors, smart contract projects typically publish their source code on blockchain explorers and verify it against the deployed bytecode, making the on-chain program accessible...

LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment

Software and systems security workflows are typically procedural: analysts inspect heterogeneous artifacts, form hypotheses, invoke tools, interpret outputs, and revise plans. Large language model LLM-based agents, which can plan, use tools, retain state, and revise actions across multi-step...

CodeMechanic: Bug-Property-Guided Program Mitigation

Automated testing discovers vulnerabilities faster than developers can investigate and repair them, leaving an interval in which known memory corruptions remain exploitable. End- to-end LLM repair agents can shorten this interval, but they synthesize open-ended code changes and commonly validate...

attackgen v0.16.0

AttackGen AttackGen is a cybersecurity incident response testing tool that leverages the power of large language models and the comprehensive MITRE ATT&CK and ATLAS frameworks. The tool generates tailored incident response scenarios based on user-selected threat actor groups, AI attack case...

Security and Privacy Taxonomy Generation from Mobile App Reviews

Mobile app reviews are a rich, continuously renewing source of how users experience privacy and security, yet existing taxonomies of these concerns are hand-crafted and cannot keep pace with the evolving nature of the data. Automating taxonomy construction is the natural response, but scalability...

OpenAnt — Updated!

OpenAnt OpenAnt from Knostic is an open source LLM-based vulnerability discovery product that helps defenders proactively find verified security flaws while minimizing both false positives and false negatives. Stage 1 detects. Stage 2 attacks. What survives is real. We're pretty proud of this...