Periodic security sweep of Atlas in four areas (MCP and CLI, the Tauri desktop shell, the web renderer and connectors, the supply chain and CI) that follows untrusted input to what it can reach, proves each reach with a planted input, and turns every confirmed finding into a fix slice with a regression test. Not for a single diff, which takes the reviewer's security lens.
Periodic security sweep of Atlas in four areas (MCP and CLI, the Tauri desktop shell, the web renderer and connectors, the supply chain and CI) that follows untrusted input to what it can reach, proves each reach with a planted input, and turns every confirmed finding into a fix slice with a regression test. Not for a single diff, which takes the reviewer's security lens.
Review the branch's pending changes for security problems against Every App's security page (docs/security.md), with pnpm security-review (Claude Code's scanner plus this repository's boundaries and false-positive rules); use before opening a pull request that touches the perimeter, identity, Cloudflare Access, OAuth, tokens or secrets.
The last gate before untrusted instruction content is ingested. Screens a skill, goal or workflow fetched from git or any remote source for prompt injection, reading it as evidence rather than as instructions, on the assumption that its author wrote it to defeat this exact review. Use before installing, enabling, updating or reviewing any agent instruction content that did not come from the user directly - registry installs, git clones, gists, pasted SKILL.md files, or a skill that pulls further files at runtime.
15448d agoReviewMountCreate a free account to mount
Security of anything using LLMs or agents: prompt injection, tool scoping, secrets, human approval, RAG, AI-generated deps (slopsquatting). \"es seguro mi bot/agente de IA\". OWASP LLM + Agentic.
Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection signature detection, and adversarial robustness scoring.
STRIDE + OWASP-based security audit with optional auto-fix. Scans code for vulnerabilities, categorizes by severity, and can iteratively fix findings using vc:autoresearch pattern.
Assess, route and report a suspected security vulnerability in Apache StreamPipes against the project's threat model. Use when a task involves a potential vulnerability, an exploit claim, a security finding from a scanner, or a decision about whether something is in or out of the security model.
7562mo agoReviewMountCreate a free account to mount
Three-tier parallel security audit (injection + auth + config, each examined by a different model tier) with severity-ranked consolidation — use when the user asks for tri-security, triple security audit, three-way security review, multi-model vulnerability scan, or parallel security audit of a code change, branch, module, or endpoint. Worth the extra cost when — touching auth/payments/user-uploads/admin surfaces, before prod deploy of security-sensitive code, after a security incident, or when the user is paranoid about a specific attack class. Do NOT use for general code quality review (use tri-review), bug diagnosis (use tri-debug), or approach comparison on greenfield work (use tri-dispatch). Do NOT use for a single-line "is this XSS safe" question, or for running pre-existing scanners like npm audit / gosec / semgrep — those are single-tool tasks, not a tri workflow.
Add stateless JWT authentication to a Symfony API with LexikJWTAuthenticationBundle — firewall wiring in security.yaml, token TTL and refresh, and a custom authenticator when the defaults are not enough. Use when the user must configure a Symfony firewall for JWT — the login entry point, the api firewall, and the token authenticator in security.yaml; the user needs to authenticate a Symfony API statelessly with JWT tokens issued and verified by LexikJWTAuthenticationBundle; the user wants to set the JWT token TTL, add refresh tokens, or build a custom Symfony authenticator for token handling. Keywords: security, auth, authentication, jwt, symfony, firewall, stateless, api.
GCP security enforcer. Reviews designs and implementations against the GCP Well-Architected Framework security pillar, OWASP Top 10, and GCP-specific risk patterns. Enforces least-privilege IAM, secrets management, no hardcoded credentials, and security-by-design. Also reviews solution-designer output for cross-cloud security gaps. Must clear the security gate before any implementation begins. Use when the user mentions: security review, IAM review, least privilege, vulnerability, public bucket, default service account, security posture, compliance GCP, OWASP GCP. Use this to review and gate; use iam instead to author or change bindings.
Entry P1 category router for API security. Use when choosing between API recon, authorization, token abuse, and hidden-parameter workflows before any deeper API topic skill.
Fix a security vulnerability without leaking it before the release. Work happens on a local-only branch that is never pushed, then merges straight into the branch the release workflow publishes from. The fix becomes public at the same moment CI publishes the release, so the package keeps npm provenance. Use this skill whenever the user asks to fix a security issue, vulnerability, advisory, CVE or GHSA, or when other work finds one, even if they do not say "security-fix".
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.