681 matches found
evtx-baseline
evtx-baseline A repository hosting example goodware evtx logs containing sample software installation and basic user interaction Donations win10-client.tgz by @phantinuss win11-client.tgz by @frack113 win7-x86.tgz by @pH-T win2022-evtx.tgz by @Neo23x0 win2022-ad.tgz by @frack113...
NotQuite0DayFriday
This repository documents real bugs in real software. At the time of disclosure the most recent versions were patched. Seeing mistakes that were made in the past can be a useful tool for seeing trends of bugs which make it past all the quality control processes. Understanding what happened, is th...
idasec
idasec IDA plugin for reverse-engineering and dynamic interactions with the Binsec platform Disclaimer IDAsec is prototype tool under development, some features are likely buggy and should be used with care. Features Decoding an instruction in DBA IR Loading execution traces generated by Pinsec...
MAccConc
Overview This is tooling for exploring Linux kernel race conditions and for general kernel debugging. See also the announcement blog post https://projectzero.google/2026/09/maccconc-race-condition.html. There are currently three tools: 1. A GUI for viewing KCOV traces of Linux kernel execution an...
jataayu
🦅 Jataayu In the Ramayana, Jataayu was the eagle who spotted Ravana abducting Sita. He didn't wait for a pattern to match. He saw the threat, judged the situation, and acted — alone, without hesitation. That's Jataayu. The runtime authorization layer for tool-using AI agents. Gate the action, not...
BoxPwnr-Traces
BoxPwnr-Traces BoxPwnr traces and benchmark results across multiple security platforms. Each trace includes the full LLM interaction, commands executed, a markdown report + attack graph, stats and config used. Browse leaderboards, replay runs in an interactive web viewer, and read AI-generated...
PrivacyTrace
PrivacyTrace How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces PrivacyTrace studies user-profile inference from MCP tool-call traces, without access to user conversations. The benchmark contains 1,000 synthetic user profiles , 4,000 agent trajectories , and 25 MCP...
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. Núñez V. AIR Institute, Salamanca and Amin Shahraki...
SMT
Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces Introduction This repository contains the official implementation of our paper: Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces If you find this repository useful for your...
EUVD-2026-125609
ragent 1.0.0 through 1.1.0 contains a missing authorization vulnerability in RagTraceController that allows any logged-in user to view all users' RAG traces. Attackers can page through /rag/traces/runs and related node endpoints to read other users' usernames, user ids, conversation ids, question...
CVE-2026-129157
The software ragent versions 1.0.0 through 1.1.0 contains a missing authorization vulnerability in the RagTraceController component. This flaw allows any authenticated user to access and view RAG traces belonging to other users. By navigating the /rag/traces/runs and related node endpoints, an at...
DHI-HXAR-KH6A-IPBX-O6KQ OpenTelemetry-Go is the Go implementation of OpenTelemetry. Prior to 1.43.0, the otlp HTTP exporters…
OpenTelemetry-Go is the Go implementation of OpenTelemetry. Prior to 1.43.0, the otlp HTTP exporters traces/metrics/logs read the full HTTP response body into an in-memory bytes.Buffer without a size cap. This is exploitable for memory exhaustion when the configured collector endpoint is...
How Much Can Tool Calls Reveal about You? Privacy Leakage from Tool-Call Traces
Large language model LLM-based agents interact with external tools through protocols such as the Model Context Protocol MCP, producing tool-call traces that may expose behavioral signals about users. In this work, we systematically study the risk of user-profile inference from MCP tool-call trace...
EUVD-2026-112031
HCL BigFix AEX is affected by an Information Disclosure vulnerability due to improper handling of errors or exceptional conditions. This could allow an attacker to obtain sensitive technical information, including stack traces, system details, or internal paths, potentially facilitating further...
CVE-2026-67080 HCL BigFix AEX is affected by multiple security vulnerabilities.
HCL BigFix AEX is affected by an Information Disclosure vulnerability due to improper handling of errors or exceptional conditions. This could allow an attacker to obtain sensitive technical information, including stack traces, system details, or internal paths, potentially facilitating further...
HCL BigFix AEX information disclosure vulnerability
The HCL BigFix AEX version 13.0.0.1 contains a security vulnerability stemming from improper error handling or abnormal condition processing. This may lead to information disclosure, allowing attackers to obtain sensitive technical details such as stack traces, system details, and internal paths,...
BIT-MLFLOW-2026-53995 MLflow 3.17.1 and prior Path Traversal via Trace ID API
MLflow 3.17.1 and earlier contains a path traversal vulnerability in the FileStore tracking backend that allows unauthenticated attackers to control filesystem paths by submitting a crafted trace ID containing traversal sequences to the POST /api/3.0/mlflow/traces endpoint. Attackers can exploit...
PT-2026-123459
MLflow 3.17.1 and earlier contains a path traversal vulnerability in the FileStore tracking backend that allows unauthenticated attackers to control filesystem paths by submitting a crafted trace ID containing traversal sequences to the POST /api/3.0/mlflow/traces endpoint. Attackers can exploit...
MLflow FileStore Trace IDs Allow Path Traversal And Arbitrary File Writes
MLflow 3.17.1 and earlier contains a path traversal vulnerability in the FileStore tracking backend that allows unauthenticated attackers to control filesystem paths by submitting a crafted trace ID containing traversal sequences to the POST /api/3.0/mlflow/traces endpoint. Attackers can exploit...
AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents
Verifying the provenance of autonomous LLM agents is a critical security challenge. Existing semantic attribution is easily obfuscated by system prompts, while active watermarking conflicts with schema-constrained tool generation. We propose AgentTrace, an active framework that identifies the...