# Security Cards

> Updated 2026-09-10 · type: tool · category: mcp-agents · status: active · rev 1

Security Cards is an open-source security-guidance dataset + agent skill for 80+ libraries, to stop coding agents writing insecure code.

- Open source: yes (Apache-2.0)
- Self-hostable: yes
- Pricing model: free
- Best for: Teams whose coding agents ship insecure code and want library-specific security guidance injected as a skill.
- Last verified: 2026-09-10

- **Canonical:** https://gtmstacker.com/registry/tool/security-cards/
- **Source:** [github · Reware-Labs/securitycards](https://github.com/Reware-Labs/securitycards)
- **Tags:** mcp-agents, agent-security, claude-skills, secure-coding, governance, dataset
- **Repository:** https://github.com/Reware-Labs/securitycards

## Is Security Cards open source?

Yes, Security Cards is open source under the Apache-2.0 license.

## How much does Security Cards cost?

Security Cards is free to use.

## Can I self-host Security Cards?

Yes, Security Cards can be self-hosted (the source is available under the Apache-2.0 license).

## Alternatives & related

- [Stroq](https://gtmstacker.com/registry/tool/stroq/)
- [Tripwire](https://gtmstacker.com/registry/tool/tripwire-agent-scanner/)


---

Open-source security-guidance dataset and installable agent skill (Astro site + data): targeted, version-aware security best practices for 80+ widely-used libraries across 13 languages, aimed at coding agents that write functionally-correct-but-insecure code. In the makers' BaxBench eval, wiring it into Claude Code (Opus 4.7) cut the insecure-code rate from 23.9% to 6.6%.

## Provenance

- Apache-2.0 independently WebFetch-verified 2026-09-10 (18★, 25 commits; repo Reware-Labs/securitycards, Astro + data/skills). Surfaced via the 2026-09-10 daily pull as the strongest individual anchor of the agent-safety cluster. The 72% figure is vendor-claimed (BaxBench).
- Curated from the GTM Stacker signal registry (2026-09-10 pass: daily pull + viral-posts brief); license independently WebFetch-verified 2026-09-10.