
MMSkillRisk
Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

Crystal port of GodPotato to abuse SeImpersonatePrivilege with indirect syscalls, dynamic API resolution and compile-time string obfuscation. Run…

Detection-aware BloodHound attack-path scoring - the quietest route to your objective, calibrated across five detection tiers…

Bash-based Linux persistence detection tool for DFIR investigations. Scans 15+ persistence mechanisms (systemd, cron, kernel modules, SSH,…

Post-exploitation framework that abuses trusted sites like Telegram and Discord for C2.

Security benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…

Heap OOB write in MariaDB JSON_SCHEMA_VALID() → persistent privilege escalation (lab-assisted)

A session-0 capable dll injection utility

Tools for get offsets and adding patch for support i386

CVE-2013-6282 kernel exploit that overwrites ptmx.fsync handler and uevent_helper string for local privilege escalation on vulnerable Linux systems.