29 tagged ai-security, measured the same way as everything else here.
Browse within: bug-bounty 61cybersecurity 58bugcrowd 52devsecops 50claude-ai 37ethical-hacking 37hackerone 37agentic-security 30attack-trees 30llm-security 29agentic-ai 23appsec 20open-source 18application-security 15
Command Claude CodeOpenCode ✓ vendor
Scan an AI agent skill for security risks with SkillSpector (static analysis by default); use when vetting a skill before install or auditing one in use.
Command Claude Code
Incident response workflow — triage, evidence collection, timeline, and IOC extraction.
Command Claude Code
Scan a package, repo, MCP server, domain, web page, or skill for security threats using the brin API.
Command Claude Code
End-of-session handoff — summarize, verify, and stage so you can review and commit.
Command Claude Code
Run deterministic verification.
Command Claude Code
Show which Anthropic credential source Assay is using.
Command Claude Code
Start hunting on a target — loads scope, reads disclosed reports, picks best attack surface based on tech stack, runs targeted vuln checks. Usage: /hunt target.com [--vuln-class ssrf|idor|xss|sqli|oauth|race|graphql|llm|upload|business-logic].
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: