Security audit of deonmenezes/bountyhunter · MCP Server by deonmenezes · ★ 80
Use with caution — bountyhunter triggered warning flags in AgentSkillsHub's security scan. It may be fine for personal trials, but review its credential handling and maintainer before brand or production use.
What it is: Mantis — autonomous offensive-security platform for Claude Code. DISCOVER → REASON → TEST → LEARN over a 7-phase FSM with parallel specialist agents, 3-round Multi-Step Evidence verification, MCP control plane. Evidence, not alerts.
docker privileged| Security grade | ⚠ CAUTION |
| Quality score | 66/100 |
| GitHub stars | 80 |
| Language | JavaScript |
| License | NOASSERTION |
| Last updated |
This is AgentSkillsHub's free basic audit: an automated rule-based scan covering SlowMist's 11 red-flag categories (credential exfiltration, obfuscated payloads, sandbox escape, prompt injection, and more) across 117,000+ open-source AI agent skills and MCP servers, refreshed every 8 hours. A CAUTION grade is a scan result, not a guarantee — deep 5-dimension audits (code · credentials · vendor · supply-chain · operational) are available for enterprise. Audited: 2026-07-03.