Lucene search
+L

128 matches found

Kitploit
Kitploit
β€’added 2026/11/20 10:31 p.m.β€’60 views

ConcoLLMic

ConcoLLMic: Agentic Concolic Execution Paper : IEEE S&P 2026 ConcoLLMic is the first language- and theory-agnostic concolic executor powered by LLM agents. Unlike traditional symbolic execution tools that require language-specific implementations and struggle with constraint solving, ConcoLLMic:...

6.4AI score
SaveExploits0References7
Kitploit
Kitploit
β€’added 2026/11/20 8:54 p.m.β€’27 views

agentic-dm-gateway

Agentic DM Gateway Security control plane for LLM agents over private chat typically Discord DMs. It sits in front of your agent. It decides who may talk, whether the session is unlocked, whether the process is paused, and whether this message is safe enough to forward. Your model and tools stay...

6.1AI score
SaveExploits0References4
Kitploit
Kitploit
β€’added 2026/11/20 7:36 p.m.β€’38 views

skyvern

πŸ‰ Automate Browser-based workflows using LLMs and Computer Vision πŸ‰ Skyvern automates browser-based workflows using LLMs and computer vision. It provides a Playwright-compatible SDK that adds AI functionality on top of playwright, as well as a no-code workflow builder to help both technical and...

6.5AI score
SaveExploits0References5
Kitploit
Kitploit
β€’added 2026/11/20 11:54 a.m.β€’102 views

anamnesis-release

Anamnesis: LLM Exploit Generation Evaluation This repository contains the evaluation framework for studying how LLM agents generate exploits from vulnerability reports in the presence of exploit mitigations. Given a bug report and proof-of-concept trigger, agents analyze vulnerable software and...

6.7AI score
SaveExploits0References9
Kitploit
Kitploit
β€’added 2026/11/20 5:50 a.m.β€’9 views

memform-code

MemForm evaluation release This repository accompanies the paper MemForm: Benchmarking Memory Formation Poisoning in LLM Agents. MemForm is a deterministic benchmark of persistent-memory poisoning in LLM agents. It asks a causal question that ordinary jailbreak or prompt-injection suites do not...

6.2AI score
SaveExploits0
Kitploit
Kitploit
β€’added 2026/11/19 10:58 p.m.β€’39 views

AgentWatcher

AgentWatcher AgentWatcher is a detection-based defense against indirect prompt injection in LLM agents. It first runs causal context attribution over untrusted context to find the most influential contexts, then applies a monitor LLM that classifies those contexts under explicit, customizable...

6.3AI score
SaveExploits0References5
Kitploit
Kitploit
β€’added 2026/11/19 5:37 p.m.β€’22 views

agenttriage-open-source

AgentTriage AgentTriage is a cross-agent tracing and security-diagnosis system for tool-using LLM agents. It observes source ingress, planning and tool lifecycles, normalizes them into one canonical event contract, reconstructs a Simplified Typed Provenance Graph STPG, extracts a source-to-sink...

6.5AI score
SaveExploits0References2
Kitploit
Kitploit
β€’added 2026/11/19 1:09 p.m.β€’28 views

llm-agent-testbed

πŸ›‘οΈ LLM Agent Security Testbed Empirical Vulnerability & Defense Harness for Tool-Calling LLM Agents A disciplined security testbed testing whether tool-equipped LLM agents can be manipulated into unauthorized data exfiltration via prompt injection, role-claim social engineering, and confused-deput...

6.3AI score
SaveExploits0
Kitploit
Kitploit
β€’added 2026/11/19 10:30 a.m.β€’34 views

ClawGuard

ClawGuard πŸ›‘οΈ δΈ­ζ–‡η‰ˆ Our Project:https://github.com/SafeAgent-Beihang/clawguard ClawGuard is a security toolkit designed to mitigate risks associated with autonomous agents, such as OpenClaw and other LLM-driven entities. As agents gain more autonomy to execute code, access APIs, and manage files,...

6.4AI score
SaveExploits0References7
Kitploit
Kitploit
β€’added 2026/11/19 6:45 a.m.β€’24 views

AgentStalker

AgentStalker Agent St atic + A ttack-graph + L ive-replay K ernel for treating an LLM agent as a system to be audited β€” not a model to be aligned. δΈ­ζ–‡η‰ˆ Β· v2 Roadmap Β· CodeWhale Audit Report Table of Contents Overview Validated in the Wild Features Current Capability Boundaries Architecture Quick...

5.9AI score
SaveExploits0References3
Kitploit
Kitploit
β€’added 2026/11/19 5:20 a.m.β€’22 views

ActGuard

ActGuard ActGuard is a pre-execution action-auditing defense against indirect prompt injection in tool-using LLM agents. This repository contains the final ActGuard implementation and the AgentDojo-based runtime needed to evaluate it. The release contains only the final, full ActGuard...

6.2AI score
SaveExploits0
Kitploit
Kitploit
β€’added 2026/11/18 12:01 p.m.β€’16 views

benign-instruction-bench

Passing the Test You Trained On Re-evaluating prompt-injection detectors where LLM agents actually use them: on the tool outputs an agent reads. Teams pick injection detectors by their benchmark scores. We check whether those scores predict behavior inside an agent, and find that they mostly...

6.1AI score
SaveExploits0
Kitploit
Kitploit
β€’added 2026/11/18 9:37 a.m.β€’26 views

ShadowMem

ShadowMem: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory This repository contains the official code release for the paper Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory. ShadowMem is a defensive framework that maintains a dedicated, safety-focused...

6.4AI score
SaveExploits0
Kitploit
Kitploit
β€’added 2026/11/18 3:08 a.m.β€’5 views

agent-trace-detector-eval

What Standard Evaluations Hide About Detectors of Hijacked LLM Agents: Rare Attacks, Unseen Tools and Benchmark Transfer Code, derived data, result files and every monitor call for the paper by Mahmoud Abbasi University of Salamanca, Juan M. NΓΊΓ±ez V. AIR Institute, Salamanca and Amin Shahraki...

6.3AI score
SaveExploits0References2
Packet Storm News
Packet Storm News
β€’added 2026/11/18 12:00 a.m.β€’4 views

PIPETTE: Prompt Injection Purple-Teaming for Robust LLM Agents

Large language model LLM agents routinely interact with untrusted external data, exposing them to indirect prompt injection IPI attacks that hijack agents into executing attacker-chosen tasks. To uncover these vulnerabilities at scale, automated red-teaming methods often leverage reinforcement...

6AI score
SaveExploits0
Packet Storm News
Packet Storm News
β€’added 2026/11/18 12:00 a.m.β€’4 views

AutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM Agents

Prompt injection is the dominant unsolved security risk for LLM agents, and the community now agrees that robustness must be measured against adaptive attackers rather than fixed benchmark injections. Many adaptive red teamers exist, and most are built to maximize attack success rate ASR. Yet ASR...

5.9AI score
SaveExploits0
Kitploit
Kitploit
β€’added 2026/11/17 6:15 a.m.β€’26 views

Defenses-for-Tool-Integrated-LLM

Universal Defences for Tool-Integrated LLM Agents Against Adversarial Attacks This repository contains the code and experiments for our project on defending tool-integrated large language model LLM agents against adversarial attacks. Overview We build upon Agent Security Bench ASB to evaluate how...

6.4AI score
SaveExploits0References1
Packet Storm News
Packet Storm News
β€’added 2026/11/09 12:00 a.m.β€’7 views

StealthyPoison: Manipulating LLM Agent Behavior through Procedural Poisoning of Third-Party Skills

LLM agents increasingly retrieve third-party skills from public registries and follow their procedures to complete user tasks. This reliance allows attackers to manipulate agent behavior by poisoning the skills. However, overtly malicious instructions can provide explicit signals for detection. W...

6.4AI score
SaveExploits0
Packet Storm News
Packet Storm News
β€’added 2026/11/09 12:00 a.m.β€’8 views

Detecting Shadow AI: Unsanctioned LLM Agents on Enterprise Endpoints: A Taxonomy, an Open Detector and a Controlled Evaluation

Shadow IT, the use of technology that the IT organisation has not approved, is a long-standing governance problem. We argue that autonomous AI agents can make it grow much faster: agents make building tools nearly free, act with their user's privileges, and leave behind scripts, automations and M...

6.1AI score
SaveExploits0
Packet Storm News
Packet Storm News
β€’added 2026/11/08 12:00 a.m.β€’8 views

Least-Privilege Auditing of Agent Tool Calls with Intent Graphs and Reasoning-Guided Escalation

LLM agents that call tools are exposed to indirect prompt injection: instructions hidden in tool outputs can steer an agent into calls the user never asked for. We present a runtime audit that derives an executable intent graph from the user's objective and the deployment's tool catalog with one...

6AI score
SaveExploits0
Rows per page
Query Builder