Spellwarden
Security checks for agent skills and MCP servers
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Your AI agents load skills and MCP servers from the internet. Spellwarden checks them first: 65 open-source rules mapped to OWASP and NIST flag prompt injection, tool poisoning, leaked secrets and unpinned packages. Findings become policy for Claude Code hooks, Kong and Zuplo. Evals show whether a skill helps, runtime traces show what agents use, and a private registry admits only what passes. Free Apache-2.0 scanner, EU-hosted, live demo with no signup.
PH · launched Nov 10, 2026 · 2 upvotes (top 19%) · 0 views
Niche: ai agent security and monitoring tools · 297 launches, 14 in the last 7 days ▼ -44% · Explore this niche →
Category and tags
- Security
- Compliance & governance
- Developer
- AI feature
- Commercial product
- Developer Tools
- Artificial Intelligence
- GitHub
- Security
Visit website ↗ Source listing ↗
More like this: all 297 launches in ai agent security and monitoring tools →
Could you build this?
Partial The scanning UI, policy export, and gateway integrations are buildable, but the 65 detection rules and their accuracy evals need real security expertise and a test corpus of malicious skills and MCP servers.
What it would actually take: The core is a static analyzer that parses agent skill files and MCP server manifests, plus a rule engine mapped to OWASP and NIST categories. Integrations with Claude Code hooks and API gateways like Kong and Zuplo are mostly plumbing. The hard part is writing rules that catch prompt injection and tool poisoning without high false positives, which requires AppSec expertise and a labeled dataset of malicious and benign examples to evaluate against.
Competitors
Other products that read as similar to this one : 773 launches clear the similarity bar, closest 8 shown.
Attention rank: #163 of 774 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 368 days after the earliest competitor.
- AgentGuard · ph · 2026-10-08 · 68 upvotes · similarity 0.55
- UNPWNED Skill Scanner · ph · 2026-10-22 · 3 upvotes · similarity 0.55
- TechIndex · ph · 2026-10-29 · 1 upvotes · similarity 0.54
- TotalHeal AgentGate · ph · 2026-11-10 · 1 upvotes · similarity 0.52
- Skills Agentes · ph · 2026-09-12 · 4 upvotes · similarity 0.51
- Claude-AgentHunter · github · 2026-10-19 · 19 upvotes · similarity 0.51
- Optimus.AI · ph · 2026-09-30 · 2 upvotes · similarity 0.51
- Risk Analysis Database of Every MCP Server · hn · 2026-02-05 · 22 upvotes · similarity 0.50
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.