bug-bounty473
google371
microsoft318
facebook271
xss267
rce184
apple178
malware177
exploit165
cve122
account-takeover110
bragging-post102
phishing85
csrf85
privilege-escalation83
browser71
supply-chain69
stored-xss65
authentication-bypass64
dos64
react58
reflected-xss57
cloudflare52
reverse-engineering50
access-control48
node48
input-validation48
aws48
cross-site-scripting48
writeup47
docker46
ssrf45
smart-contract45
ethereum44
web-security43
sql-injection43
defi43
web343
oauth41
web-application41
lfi38
info-disclosure37
pentest37
race-condition37
idor35
burp-suite35
auth-bypass35
vulnerability-disclosure34
cloud34
html-injection33
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