Claude skills and agent skills

OpenAISkill

security-threat-model

openai/skills/skills/.curated/security-threat-model/SKILL.md

Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.

JeffallanReads credentialsSkill

secure-code-guardian

Jeffallan/claude-skills/skills/secure-code-guardian/SKILL.md

Use when implementing authentication/authorization, securing user input, or preventing OWASP Top 10 vulnerabilities — including custom security implementations such as hashing passwords with bcrypt/argon2, sanitizing SQL queries with parameterized statements, configuring CORS/CSP headers, validating input with Zod, and setting up JWT tokens. Invoke for authentication, authorization, input validation, encryption, OWASP Top 10 prevention, secure session management, and security hardening. For pre-built OAuth/SSO integrations or standalone security audits, consider a more specialized skill.

amdSkill

security-assessment

amd/gaia/.claude/skills/security-assessment/SKILL.md

Assess a reported security vulnerability in GAIA and fill a PSIRT / JIRA triage: decide if it is valid & exploitable, whether it needs a CVE + bulletin, and produce the CVSS 4.0 score, CWE, and CVE description. Use when triaging a researcher report, a security advisory, or a claude-security-audit finding — anytime you must answer 'is this a CVE?' or produce a CVSS score/vector/severity. Always COMPUTES the score from a reviewed vector with util/cvss4.py (matches the FIRST 4.0 calculator); never guess the number — an LLM's guessed CVSS number is untrustworthy.

MicrosoftSkill

fix-security-issues

microsoft/fluentui-react-native/.github/skills/fix-security-issues/SKILL.md

Audit and remediate dependency security advisories while respecting package age policy, removing unused vulnerable capabilities, deduplicating Yarn resolutions, and validating affected tooling.

NVIDIASkill

review-security-issue

NVIDIA/OpenShell/.agents/skills/review-security-issue/SKILL.md

Review an authorized security issue or private GitHub advisory for validity, severity, and a remediation plan.

No other project uses it yet

SentrySkill

gha-security-review

getsentry/skills/skills/gha-security-review/SKILL.md

GitHub Actions security review for workflow exploitation vulnerabilities. Use when asked to "review GitHub Actions", "audit workflows", "check CI security", "GHA security", "workflow security review", or review .github/workflows/ for pwn requests, expression injection, credential theft, and supply chain attacks. Exploitation-focused with concrete PoC scenarios.

orangehrmSkill

security-primitives

orangehrm/orangehrm/.agents/skills/security-primitives/SKILL.md

Reference for OrangeHRM's cryptographic and password-handling primitives — the `Cryptographer` class (AES-256-GCM with random nonces for new ciphertext, legacy AES-128-ECB still accepted on decrypt for backward compatibility), `KeyHandler` for the file-based crypto key lifecycle (created at install when data encryption is enabled, stored at `lib/confs/cryptokeys/key.ohrm`), `EncryptionHelperTrait` for accessing the Cryptographer from EntityListeners with the `encryptionEnabled()` guard, `PasswordHash` wrapping PHP's `password_hash`/`password_verify` with `PASSWORD_BCRYPT` cost 12, the `GCMAES256.` prefix marker that distinguishes new vs legacy ciphertext, the encrypt-on-write + decrypt-on-read symmetric round-trip pattern via EntityListeners, and the CSRF token handling via Symfony's `CsrfTokenManagerTrait`. Use whenever the user is adding a new sensitive column that needs encryption, debugging crypto failures, asking about key rotation, handling passwords, or implementing CSRF protection. Companion to `entities` (EntityListener side of encryption), `migrations` (column sizing — ciphertext needs 512 chars), `config` (where OAuth encryption keys are stored).

MicrosoftSkill

supply-chain-security

microsoft/apm/.agents/skills/supply-chain-security/SKILL.md

Activate when reviewing or modifying dependency resolution, lockfile schema, package downloaders, signature/integrity checks, file integration cleanup, or anything that could expose APM to dependency confusion, typosquatting, malicious packages, or token leakage.

Often used withbinary-diff·pentest-tools·js-reverse

MicrosoftSkill

supply-chain-security

microsoft/apm/.apm/skills/supply-chain-security/SKILL.md

Activate when reviewing or modifying dependency resolution, lockfile schema, package downloaders, signature/integrity checks, file integration cleanup, or anything that could expose APM to dependency confusion, typosquatting, malicious packages, or token leakage.

Often used withbinary-diff·pentest-tools·js-reverse

penpotReads credentialsSkill

security-and-hardening

penpot/penpot/.agents/skills/security-and-hardening/SKILL.md

Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.

Often used withconstraint-driven-development·observability-and-instrumentation·doubt-driven-development

MaxMiksaReads credentialsSkill

code-review-security

MaxMiksa/Auto-Company/.claude/skills/code-review-security/SKILL.md

Security-focused code review checklist and automated scanning patterns. Use when reviewing pull requests for security issues, auditing authentication/authorization code, checking for OWASP Top 10 vulnerabilities, or validating input sanitization. Covers SQL injection prevention, XSS protection, CSRF tokens, authentication flow review, secrets detection, dependency vulnerability scanning, and secure coding patterns for Python (FastAPI) and React. Does NOT cover deployment security (use docker-best-practices) or incident handling (use incident-response).

Often used withcommunity-led-growth·micro-saas-launcher·ux-audit-rethink

ruvnetSkill

agent-v3-security-architect

ruvnet/claude-flow/.agents/skills/agent-v3-security-architect/SKILL.md

Agent skill for v3-security-architect - invoke with $agent-v3-security-architect

kedro-orgDeletes or force-pushesSkill

kedro-security-review

kedro-org/kedro/.agents/skills/kedro-security-review/SKILL.md

Run a Kedro security scan on the full codebase or just a pull request. This skill always runs Semgrep first and then evaluates the findings against the Kedro security model. Use when the user says things like "run security scan on the full codebase" or "run security scan on this PR". Produce one final report only, in chat by default or posted to GitHub when explicitly asked.

SnailSploitSkill

offensive-ai-security

SnailSploit/Claude-Red/Skills/ai/offensive-ai-security/SKILL.md

SKILL: AI Pentest ## Metadata - **Skill Name**: ai-security - **Folder**: offensive-ai-security - **Source**: https://github.com/SnailSploit/offensive-checklist/blob/main/ai.md ## Description AI/LLM security offensive checklist: prompt injection, jailbreaking, model extraction, training data poisoning, adversarial

elementalsoulsSkill

email-domain-security

elementalsouls/Claude-OSINT/skills/email-domain-security/SKILL.md

Rigorous, defensible email-spoofability verdict and SPF supply-chain risk analysis computed from published DNS alone. Deepens the record-level SPF/DMARC/DKIM/BIMI/MTA-STS/DNSSEC fetch recipes in the offensive-osint arsenal (§16.14) with the reasoning that section doesn't do: a priority-ordered composite verdict for whether an attacker can actually land header-From-spoofed mail in an inbox, and by which vector (exact-domain vs subdomain) — grounded in the single most-misunderstood distinction in email security: the envelope MAIL FROM that SPF authenticates vs the visible header From: that only DMARC governs. Explains precisely why SPF -all/~all alone is NOT spoof-proof without DMARC enforcement, and why SPF +all bypasses DMARC even under p=reject pct=100. Covers RFC 7208 §4.6.4's 10-DNS-lookup / 2-void-lookup PermError fail-open condition with a runnable stdlib-only lookup-counter script, plus the SPF-include-takeover supply-chain vector (an attacker re-registering a dead include inherits SPF-pass authority over the victim domain) with strict transient-vs-NXDOMAIN discrimination discipline so a temporary SERVFAIL is never mistaken for a takeover lead. Fully passive: DNS TXT reads only, no mail sent, no RCPT TO probe, no API keys. Use when auditing a domain's real spoofing resistance (not just its published records), explaining to a client why 'we have SPF -all' does not mean they're covered, investigating an SPF PermError or an unusually long include chain, evaluating a dead SPF include as a takeover lead, or writing a defensible spoofability finding for a deliverable.

symfonySkill

symfony-security-review

symfony/symfony/.agents/skills/symfony-security-review/SKILL.md

Review a change (a PR, the current branch diff, or a set of files) or audit a component or the whole tree for missing or incorrect security hardening. Reasons about trust boundaries from first principles, then checks the code against Symfony's hardening-invariant families and runs the .github/sa-tools gates. Use when the user says "security review", "security audit", "check hardening", "review this PR/branch for security", "audit <component> for <vuln class>", "is any hardening missing", or names a vulnerability class to hunt for.

redhat-etReads credentialsSkill

ripwire-security-scan

redhat-et/ripwire/skills/ripwire-security-scan/SKILL.md

Security review: (1) vet an untrusted SKILL.md or .mcp.json BEFORE installing it — the injection/exfiltration scanner; CRITICAL blocks the install; (2) audit code on an untrusted-input path (a deserializer, parser, exec of user data, network endpoint): taint reach, untested seams. One scan pass is the verdict.

No other project uses it yet

lukevellaReads credentialsSkill

better-auth-security-best-practices

lukevella/rallly/.agents/skills/better-auth-security-best-practices/SKILL.MD

This skill provides guidance for implementing security features that span across Better Auth, including rate limiting, CSRF protection, session security, trusted origins, secret management, OAuth security, IP tracking, and security auditing. These topics are not covered in individual plugin skills.

ipxeSkill

ipxe-security-review

ipxe/ipxe/.claude/skills/ipxe-security-review/SKILL.md

Systematic memory-safety review of iPXE's attacker-facing parsers. Use when asked to hunt for vulnerabilities, audit a network-input parser, or review a FILE_SECBOOT(PERMITTED) file that handles DHCP / DNS / TFTP / HTTP / TLS / EAP / PeerDist data or downloaded images, for length, overflow, or underflow defects.

OpenAISkill

security-ownership-map

openai/skills/skills/.curated/security-ownership-map/SKILL.md

Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions.