bug-bounty451
google354
xss338
microsoft283
facebook246
apple171
exploit163
rce160
malware102
account-takeover95
cve91
bragging-post86
csrf83
browser77
writeup75
privilege-escalation68
react60
authentication-bypass57
cloudflare54
dos53
node52
docker51
ssrf51
phishing50
aws48
access-control47
oauth45
smart-contract45
supply-chain44
ethereum43
defi42
web342
sql-injection41
lfi37
idor35
vulnerability-disclosure32
smart-contract-vulnerability32
clickjacking31
burp-suite31
info-disclosure31
race-condition31
web-application31
reverse-engineering31
wordpress30
input-validation30
web-security29
information-disclosure29
cloud29
reflected-xss29
solidity27
0
7/10
research
A 2-week empirical study of six autonomous AI agents with real tools (email, shell, persistent storage) tested by 20 researchers in both benign and adversarial scenarios, documenting 10 security vulnerabilities (prompt injection, identity spoofing, non-owner compliance, social engineering bypass) and 6 cases of emergent safety behavior including cross-agent safety coordination without explicit instruction.
ai-security
autonomous-agents
prompt-injection
social-engineering
adversarial-testing
language-models
vulnerability-research
safety-evaluation
email-security
shell-access
persistent-memory
multi-agent-systems
access-control
identity-spoofing
denial-of-service
data-exposure
constraint-bypassing
emergent-behavior
Natalie Shapira
OpenClaw
Kimi K2.5
Claude Opus 4.6
ProtonMail
Discord
GitHub
Ash
Flux
Jarvis
Quinn
Mira
Doug