Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.
Vulnerability scanner for AI agent skills. Detects prompt injection, malware patterns and OWASP LLM Top 10 issues before your agent installs an untrusted skill. As AI agents increasingly install and execute third-party skills, supply chain security becomes a real problem. SecurityScan lets an agent verify a skill's safety autonomously — no human in the loop required. Prompt injection patterns…
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.
Vulnerability scanner for AI agent skills. Detects prompt injection, malware patterns and OWASP LLM Top 10 issues before your agent installs an untrusted skill. As AI agents increasingly install and execute third-party skills, supply chain security becomes a real problem. SecurityScan lets an agent verify a skill's safety autonomously — no human in the loop required. Prompt injection patterns Malicious code indicators Data exfiltration attempts Unauthorized external API access Supply chain…