bug-bounty622
facebook468
xss316
google162
microsoft106
rce105
apple69
csrf61
web354
account-takeover54
writeup51
exploit43
sqli41
cve37
ssrf35
dos33
cloudflare33
malware30
privilege-escalation29
defi28
smart-contract-vulnerability25
node24
idor24
subdomain-takeover24
smart-contract23
clickjacking23
ethereum23
access-control21
vulnerability-disclosure21
browser20
auth-bypass20
lfi19
aws19
remote-code-execution18
docker17
reverse-engineering17
react17
cloud17
oauth16
cors16
race-condition16
info-disclosure15
solidity14
authentication-bypass14
phishing13
supply-chain13
wordpress12
denial-of-service11
delegatecall11
sql-injection11
0
5/10
Part 2 of a security benchmark study comparing LLM-based security scanners (Neo, Claude Code) against traditional SAST/DAST tools on AI-generated code, finding that Neo detects more true positives with fewer false positives by validating findings against running applications.
sast
dast
code-analysis
llm-security
vulnerability-detection
ai-generated-code
security-tooling
benchmark
static-analysis
dynamic-analysis
ProjectDiscovery Neo
Claude Code