bug-bounty486
xss278
google242
microsoft219
facebook199
rce175
malware156
exploit144
apple122
cve121
bragging-post113
account-takeover112
privilege-escalation92
csrf86
phishing81
authentication-bypass74
stored-xss74
open-source64
reflected-xss62
access-control59
supply-chain57
web-security57
dos56
browser55
ai-agents52
writeup52
input-validation51
reverse-engineering50
defi48
cross-site-scripting47
smart-contract47
ssrf45
sql-injection44
ethereum44
cloudflare42
web340
lfi39
race-condition39
web-application38
react38
oauth38
api-security38
information-disclosure37
burp-suite36
aws35
ctf34
pentest34
smart-contract-vulnerability33
auth-bypass33
tool33
0
6/10
Cisco security researchers demonstrate critical vulnerabilities in OpenClaw, a personal AI agent framework, including prompt injection, data exfiltration, and command injection attacks via malicious skills; researchers released an open-source Skill Scanner tool to detect security issues in AI agent skills, revealing 26% of analyzed skills contained at least one vulnerability.
ai-agents
prompt-injection
data-exfiltration
privilege-escalation
supply-chain-risk
malicious-skills
command-injection
credential-leakage
local-execution
security-scanning
threat-analysis
OpenClaw
Clawdbot
Moltbot
Cisco
Cisco AI Threat and Security Research
Claude Skills
OpenAI Codex
Skill Scanner
What Would Elon Do?
Anthropic
Amy Chang
Vineeth Sai Narajala
Idan Habler