bug-bounty371
xss316
google239
microsoft202
facebook194
apple135
exploit110
rce99
csrf78
malware62
account-takeover60
writeup59
bragging-post57
authentication-bypass55
browser53
access-control49
defi48
cve47
smart-contract47
ethereum44
privilege-escalation43
open-source42
sql-injection39
ssrf38
web338
ai-agents35
docker35
dos34
aws33
smart-contract-vulnerability33
supply-chain32
phishing30
idor30
react28
denial-of-service28
information-disclosure27
api-security27
solidity25
cloudflare25
burp-suite25
clickjacking25
oauth24
race-condition23
sqli23
node23
wordpress23
remote-code-execution22
vulnerability-disclosure22
reverse-engineering21
web-security21
0
2/10
Cursor describes CursorBench, an internal evaluation suite for measuring AI coding agent quality using real developer workflows rather than public benchmarks. The approach combines offline evals on private task data with online metrics to better distinguish between models and align with actual developer experience.
Cursor
CursorBench
SWE-bench Verified
OpenAI
GPT-5
Haiku
Cursor Blame
0
1/10
An open-source library of 125 GTM skills for AI coding agents (Claude Code, Codex, Cursor) that automate sales and marketing workflows like lead generation, cold email sequences, competitor monitoring, and SEO page generation through structured markdown playbooks.
Claude Code
OpenAI Codex
Cursor
Gooseworks
goose-skills