API security testing covering OWASP API Top 10 with active exploitation. Use when the user wants to test REST APIs, GraphQL endpoints, or API security.
Source-to-sink taint analysis with adversarial mindset for finding real, exploitable vulnerabilities — not theoretical ones. Use before production deploys, when editing auth/session/payment/permission/upload/middleware code, on-demand security audits, or CI/CD pre-merge checks. Pairs with Rex agent for Red/Blue team execution.
AI DevKit · Review code, skills, and prompts for security vulnerabilities — OWASP Top 10, prompt injection, business logic flaws, and insecure defaults. Use when reviewing PRs, auditing modules, reviewing AI skills/prompts, or preparing for release.
Threat-model and audit a codebase, commit range, or pull request for exploitable vulnerabilities, prompt and data injection, authentication or authorization bypass, tenant-data exposure, privilege escalation, malicious code/backdoors, unsafe execution, secrets leakage, supply-chain and CI compromise, insecure persistence, and denial of service. Use for dedicated security reviews, release gates, suspicious contributions, or requests to verify that a project protects users and their data.
Perform a targeted privacy and integrity audit of an openreview-py stage, process function, builder, journal flow or helper, tracing the readers, signatures, emails and edges it produces for every venue setting and reproducing findings with an integration test. Use when asked to audit security, check who can see a note or an identity, verify anonymity, review conflict detection or assignment visibility, assess a workflow stage end to end, or when the request mentions threat model, data leak, deanonymization or attack surface for any part of this codebase. For reviewing a pull request diff rather than auditing a whole feature, use the code-review skill instead.
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions. Use when auditing a .claude/ directory — CLAUDE.md, settings.json, MCP servers, hooks, or agent definitions.
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities
Manage Redpanda authentication and authorization from the CLI with the `rpk security` command group, and look up security settings in the Redpanda docs. Use when the user wants to create, rotate, or delete SASL/SCRAM users, grant or revoke ACLs and RBAC roles, change Redpanda Cloud secrets, turn on SASL or OIDC or Kerberos or mTLS authentication, or set up Enterprise security features like audit logging, group-based access control, and FIPS mode. For Schema Registry ACL patterns, see /redpanda:rpk-registry, and for the Enterprise license itself, see /redpanda:rpk-cluster.
Use for authorized database security assessment covering PostgreSQL/MySQL/MSSQL/Mongo/Redis exposure, authz, UDF/command paths, and misconfiguration review.
45k2d agoReviewMountCreate a free account to mount
Use for authorized hardware and embedded interface security research including UART/JTAG discovery, debug pad triage, secure boot overview, and offline firmware extraction support.
45k2d agoReviewMountCreate a free account to mount
Triage a draft security advisory in colinhacks/zod — a private vulnerability report from the Security tab, named by GHSA id (GHSA-xxxx-xxxx-xxxx) or reached from "the draft advisories", "the security reports", "the vulnerability queue". Use instead of the `triage` skill whenever the ticket is an advisory rather than a public issue or PR, because the workflow is different: the report is private, the burden of proof is on the reporter, the fix must be LANDED before any comment is drafted, and the publish-or-decline call has its own calculus. Covers reproducing a PoC against main, the schema-vs-input test, deduplicating a cluster of reports into distinct defects, landing the fix first, the publish-vs-decline framework, per-reporter privacy rules that make a GHSA id unlinkable, and the results.md format under .triage/advisories/GHSA-xxxx-xxxx-xxxx/.
Steady5 mentions in 2 weeks
4 projects use a version of this
44k2mo agoReviewMountCreate a free account to mount
Use when registering or handling WordPress AJAX over admin-ajax.php - wp_ajax_{action} / wp_ajax_nopriv_{action} hooks, JavaScript that posts to admin_url('admin-ajax.php'), or wp.apiFetch / fetch calls to custom actions. Verifies the nonce with check_ajax_referer, gates the action with current_user_can, unslashes and sanitizes every field, and replies with wp_send_json_success / wp_send_json_error. Prevents CSRF, broken access control, and injection on the AJAX surface.
452mo agoReviewMountCreate a free account to mount
Runs a repository or path security scan and produces a severity-ranked report covering hardcoded secrets and credential patterns, dependency CVEs via npm audit and equivalents, OWASP code patterns such as SQL injection, XSS, SSRF, path traversal and insecure deserialization, unsafe file permissions, and missing HTTP security headers. Use when a scan, audit, or vulnerability check is actually being asked for — /security-scan, scan for vulnerabilities, security audit, check for leaked secrets — or before shipping new code that adds authentication, cryptography, input handling, SQL, or file uploads. Reading, explaining, or editing code that merely happens to touch auth or SQL does not warrant it, since it emits a full scan report rather than an inline observation.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.