
AgentWatcher
Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…
adversarial-attackai-securityeducation+2
9

Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…

Proof-of-concept exploit for CVE-2025-27591, a local privilege escalation in the 'below' system monitor. Demonstrates symlink attack on log file to…

PoC funcional de CVE-2026-17106 (CopyEscape): carrera TOCTOU en docker cp que permite escritura arbitraria en el host Docker. Laboratorio Docker +…

A collection of useful links for Pentesters

Simulated a real-world attack (CVE-2011-2523) against a vulnerable host, then cross-checked detection coverage against an existing…