
DeepTrap
Security benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…
adversarial-attackai-securitycommand-and-control+8
11

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

CVE-2025-14847 explaination and lab

Challenge based on CVE-2021-22204 where users send a malicious file to a web application to gain RCE

Local PoC for CVE-2026-54686 demonstrating DCS lifecycle hook spoofing in Warp terminal. Simulates spoofed CWD and SSH metadata acceptance in…