Security Scanner for Agent Skills and MCP
Details
- External ID
- 47999709
- Source
- HN
- Company
- —
- Product
- A security scanner for AI Agent Skills
- Website domain
- github.com
- Launched
- May 3, 2026
- Cohort
- —
- Upvotes
- 7
- Upvotes percentile
- 0.4168012924071082
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Enrichment
- Theme
- ai cybersecurity and penetration testing
- Vertical
- Security
- Function
- —
- Audience
- Developer
- AI stance
- Not AI
- Project type
- Commercial product
- Normalized one-liner
- security scanner for ai agents
- Manually corrected
- False
Could you build this?
Yes A security scanner inspecting MCP (Model Context Protocol) tool declarations or skill manifests is essentially a rule-based AST/regex parser checking for prompt injection, sensitive permissions, or shell execution risks.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one — 1519 launches clear the similarity bar, closest 8 shown.
Attention rank: #799 of 1520 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 184 days after the earliest competitor.
- Scan your AI agents for dangerous capabilities · hn · 2026-07-06 · 44 upvotes · similarity 0.63
- heimdall-pentest · github · 2026-09-14 · 67 upvotes · similarity 0.62
- MCP Security Scanning Tool for CI/CD · hn · 2025-11-25 · 12 upvotes · similarity 0.61
- Corgea: Agentic Pentesting · yc · 2026-06-24 · 18 upvotes · similarity 0.60
- Reusable MCP Playbooks for AI Agents · hn · 2025-10-31 · 9 upvotes · similarity 0.59
- Agent-password · hn · 2026-03-21 · 5 upvotes · similarity 0.59
- flick-computer-use · github · 2026-09-24 · 22 upvotes · similarity 0.59
- jev-security-scan · github · 2026-09-19 · 10 upvotes · similarity 0.59