Official Anthropic Agent Skills repo with document and example packs
Security and Hardening
SkillDefensive coding checklist for agents: untrusted input, auth, secrets, deps, and privacy.
Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.
Product badge
Share this product's name and rating in your README or on your website.
Updates may be delayed by image caching.
About Security and Hardening
From Addy Osmani's agent-skills pack.
A defensive, build-time skill. When the agent writes input handlers, login flows, session handling, or third-party integrations, it checks the work against common web risks like the OWASP Top Ten, treats secrets carefully, triages dependency audit findings, and flags privacy concerns such as GDPR or CCPA. It's about hardening your own app, not attacking anyone else's.
No reviews yet
Used it? Write the first review.
Similar skills
Official Browserbase skills for cloud browser automation
Production agent skills from Matt Pocock's .agents directory
Build and review ASP.NET Core apps with current official guidance
Official OpenAI Agent Skills for Codex and ChatGPT workflows
Translate Figma into production code at 1:1 fidelity