Securitycards
Apply version-specific secure coding guidance to AI-generated or human-written code that uses supported open source libraries. Use when starting a software project, implementing a security-sensitive feature, or reviewing code for secure defaults, authentication, authorization, input handling, injection, cryptography, file handling, network boundaries, secrets, sessions, and other library-specific security concerns.
Install
npx skills add Reware-Labs/securitycards --skill securitycardsgit clone --depth 1 https://github.com/Reware-Labs/securitycards.git /tmp/securitycards
mkdir -p ~/.claude/skills
cp -r /tmp/securitycards/skills/securitycards ~/.claude/skills/securitycardsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Security Cards Version-pinned secure-coding rules for open source libraries, served live from `https://securitycards.rewarelabs.com`. Fetch the rules for the versions the project actually uses, then apply them. This skill is an index and a workflow, not an offline security knowledge base. ## Fetching Every URL here returns plain text or Markdown meant to be read as-is. Use whatever gives you the raw response — a shell fetch such as `curl -fsS <url>` works well. A fetch tool that summarizes pages returns the rules as prose with the code examples and URLs stripped out, which is not enough to act on. Get the raw text, or tell the user you cannot and stop. ## Resolve the version Take the exact installed version from the lockfile or the installed package. A manifest range, a requested version, or a remembered one is not enough — guidance differs between releases. For a new project, choose a supported version from the catalog, install it, then read the resolved version back before applying anything. ## Find the cards Fetch `https://securitycards.rewarelabs.com/llms.txt`, which lists one catalog per language. Fetch the catalog for your language, e.g. `https://securitycards.rewarelabs.com/llms/python.txt`. A language catalog holds one line per supported library version: ``` <library> <version> <prefix> <category>... ``` Find the line where library and version both match. `<prefix>` is a URL prefix with no trailing slash; append to it for raw Markdown:
Details
- Skill name
securitycards- Repository
- Reware-Labs/securitycards
- Path
skills/securitycards/SKILL.md- License
- Apache-2.0
- Repo updated
- 6 October 2026
- Listed in
- heilcheng/awesome-agent-skills
FAQ
What does the Securitycards skill do?
Apply version-specific secure coding guidance to AI-generated or human-written code that uses supported open source libraries. Use when starting a software project, implementing a security-sensitive feature, or reviewing code for secure defaults, authentication, authorization, input handling, injection, cryptography, file handling, network boundaries, secrets, sessions, and other library-specific security concerns.
How do I install the Securitycards skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Reware-Labs/securitycards --skill securitycards. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Securitycards popular?
It lives in Reware-Labs/securitycards, which has 21 GitHub stars and 2 forks, and is included in 1 curated skill list.
Related skills
Threat Modeling
49mn-youssef/security-skills
Use when starting a security assessment and you need to map an application's attack surface, enumerate trust boundaries, and rank what to test first — before auditing code or running tools. Produces a prioritized target list.
Security Testing
49mn-youssef/security-skills
Use when you want to security-test, pentest, audit, or find vulnerabilities in an application you own or are authorized to test — entry point that confirms authorization and routes to the right phase (threat model, code audit, active test, or hardening).
Vulnerability Chaining
49mn-youssef/security-skills
Use when you have multiple findings and need to combine them into realistic end-to-end attack paths — turning several low/medium issues into a single critical-impact exploit chain. The red-team-lead skill that ties the specialists' findings together into business impact.
Security Hardening
49mn-youssef/security-skills
Use when you have a security finding (from code audit or pentest) and need to fix it correctly with secure-coding patterns, then verify the fix actually closes it. Covers fixes for injection, access control, XSS, auth, secrets, and config across the stack.
Security Hierarchy Trace
49dynamics365ninja/d365fo-cli
Trace D365FO security from a Role all the way down to Entry Points, discover which roles reach a given object, or scaffold new security objects (privilege, duty, role, XDS policy). Use when the user asks about permissions, security coverage, roles, duties, privileges, "create a security privilege", "scaffold a security role", "generate a duty", or "create a security policy".
Security Code Audit
49mn-youssef/security-skills
Use when you have application source code and want to find security vulnerabilities by reading it — covers OWASP Top 10 across frontend, backend API, and database. Produces a findings register with severity, file:line, and exploitability.
Browse the most popular Claude skills, all security skills, or write your own with the skills generator.