Security

eunomia-bpf Bundle

Start, orchestrate, or resume an autonomous research project through hierarchical EXPERIMENT, WRITE, and REVIEW gates. Use when running a project from a rough idea to a complete paper, recovering after context loss, deciding which gate or inner loop must run next, auditing whether a specialist loop actually completed, or maintaining timestamped research provenance. Keeps the current paper under docs/paper/; step and outer-audit reports are optional. Do not use for standalone prose editing, a one-off literature summary, isolated experiment planning, or ordinary paper review without lifecycle orchestration.

finnley07 Skill

Runs a structured code review of a diff, pull/merge request, branch, or file set for correctness bugs, error-handling quality, readability/maintainability, API & contract design, test coverage, documentation accuracy, and version-control hygiene — then reports the results as one table (check, area, status, evidence, recommendation). Explicitly does not cover application security (injection, auth, access control, secrets, SSRF — that's the cybersecurity-check skill) or performance/resource efficiency (algorithmic complexity, N+1 queries, memory/CPU usage — that's the performance-audit skill). Use this whenever the user asks for a "code review", "review this PR", "review this diff", "review my code", "review this pull request", "review this merge request", "MR review", "code quality check", "quality audit", "maintainability review", "readability review", "review my changes", "sanity-check this code", "code smell check", "find code smells", "refactor candidates", "test coverage review", "is this well tested", "c

finnley07 Skill

Runs a comprehensive third-party dependency health check across every package manager and manifest in a project (npm/yarn/pnpm, pip/poetry/Pipenv, NuGet, Maven/Gradle, Cargo, Go modules, Composer, RubyGems, CocoaPods/SwiftPM, and container base images where relevant), then reports the results as one table (check, area, status, evidence, recommendation). Covers known vulnerabilities/CVEs (native audit tooling per ecosystem), outdated packages (patch/minor vs. major, migration risk), license compliance (copyleft/GPL/AGPL/LGPL conflicts with closed-source distribution, missing/unknown licenses), unused and dead dependencies, lockfile integrity and manifest/lockfile drift, reproducibility of installs, and supply-chain risk signals (unmaintained packages, single-maintainer risk, suspicious/low-download additions, install/postinstall scripts as an attack vector, typosquatting-risk names), plus whether automated update tooling (Dependabot/Renovate or equivalent) is configured. Use this whenever the user asks for a "

finnley07 Skill

Runs a structured, evidence-based review of API contract design and cross-endpoint consistency across REST, GraphQL, and gRPC surfaces — resource/endpoint naming and HTTP verb correctness, status-code correctness, request/response shape and envelope consistency, error-response format, pagination and filtering conventions, idempotency, versioning strategy, backward compatibility, and documentation/spec-vs-code drift (OpenAPI/Swagger, GraphQL SDL, .proto), plus GraphQL-specific checks (N+1-shaped resolver design, @deprecated usage, query depth/complexity limiting) and gRPC-specific checks (proto field-number stability, proto3 optional/wrappers, service/method naming). This is a design/contract-consistency review, not an authentication/access-control security review (use cybersecurity-check for that) and not a latency/throughput performance review (use performance-audit for that). Use this whenever the user asks for an "API design review", "API review", "API-Design prüfen", "API-Design-Review", "REST API check",

finnley07 Skill

Generates a structured, concrete test plan (test cases) for a specific feature, change, user story, requirements document, API contract, or code diff — the generative counterpart to this repo's audit skills. Given real source material (acceptance criteria, a user story, a requirements doc, an API/schema contract, or the actual code diff/implementation), it produces a document with prioritized (P0/P1/P2) test cases covering happy-path, negative, boundary/edge, and state-transition scenarios, plus assumptions, scope, test data needs, non-functional flags, and requirement-to-test-case traceability. It does NOT produce an audit findings table and does NOT review a project's overall test strategy/infrastructure — that is `test-strategy-audit`'s job; this skill is scoped to one feature/change, not the whole project. Use this whenever the user asks to "generate a test plan", "write test cases", "create test cases for this feature", "write a test plan for X", "test case generator", "QA test plan", "acceptance test pl

florianbruniaux Skill

Complete on-page audit of a single URL in one pass, combining heading structure, internal linking, technical meta tags, content quality and schema, then cross-checked against real Search Console data before any recommendation is made. Use when asked for a full page audit, an all-in-one check, or what to fix on a page. Aussi déclenché en français par "audit complet de cette page", "tout ce qui cloche sur cette page", "qu'est-ce que je corrige sur cette URL", "audit on-page", "passe cette page au peigne fin", "check complet", "audit tout-en-un".

florianbruniaux Skill

Audit structured data (schema markup) across the top pages to surface errors blocking rich results eligibility. Use when asked about rich results, schema errors, or structured data health. Aussi déclenché en français par "données structurées", "balisage schema", "mes rich results marchent pas", "extraits enrichis", "les étoiles dans Google", "JSON-LD", "mon FAQ s'affiche pas dans Google".

florianbruniaux Skill

Audit the heading structure of a page. Checks H1 uniqueness, level jumps, whether the title duplicates the H1 word for word, headings that carry no information, and subheading density. Use when asked about headings, H1, H2, title tags, or page structure. Aussi déclenché en français par "mes balises H1", "structure de titres", "j'ai deux H1", "hiérarchie des titres", "mon title et mon H1", "balises Hn", "est-ce que mes titres sont bons", "audit des balises".

florianbruniaux Skill

Audit sitemap health and coverage across all submitted sitemaps. Use when asked about sitemap issues, submitted vs. indexed counts, or sitemap errors. Aussi déclenché en français par "mon sitemap est à jour", "problème de sitemap", "pourquoi les URLs de mon sitemap sont pas indexées", "combien d'URLs soumises contre indexées", "mon plan de site".

florianbruniaux Skill

Audit indexing status with a site-wide overview first, then per-page deep-dive on top pages. Use when asked about crawling, indexing issues, or whether pages are indexed by Google. Aussi déclenché en français par "pourquoi mes pages sont pas indexées", "problème d'indexation", "mes pages sont pas dans Google", "Google ne crawle pas mon site", "combien de pages indexées", "découverte mais non indexée", "explorée mais non indexée", "est-ce que Google voit mes pages", "audit d'indexation".

florianbruniaux Skill

Full diagnostic for a single URL combining indexing status, search performance, Core Web Vitals, and query breakdown. Use when asked to analyze a specific page or diagnose why a particular URL is underperforming. Aussi déclenché en français par "analyse cette page", "diagnostic complet de cette URL", "pourquoi cette page ne ranke pas", "qu'est-ce qui cloche sur cette page", "cette page marche pas", "audit de cette page".

florianbruniaux Skill

Map internal link flow across a whole site and cross it with Search Console to find the pages sitting on page two that no page body links to. Site-wide companion to internal-linking-audit, which works on a single URL. Use when asked about site architecture, orphan pages, or where to place internal links. Aussi déclenché en français par "maillage de tout mon site", "quelles pages ont besoin de liens", "cartographie mes liens internes", "mes pages orphelines sur tout le site", "où placer des liens pour gagner des positions", "architecture de mon maillage".

florianbruniaux Skill

Audit internal linking on a page, weighted by where each link sits. A link in the body of a page carries far more weight than the same link in the footer or the main nav. Surfaces targets linked only from footer/nav, generic anchors, and internal nofollow. Use when asked about internal links, anchor text, link placement, or orphan pages. Aussi déclenché en français par "maillage interne", "mes liens internes", "liens en footer", "texte d'ancre", "où placer mes liens", "pages orphelines", "est-ce que mes liens sont bien placés", "audit du maillage".

graphistry Skill

Review a pull request or branch for correctness, regressions, tests, security, and repository conventions. Use when asked to review a PR, inspect a branch diff, summarize review findings, or prepare GitHub review comments.

linhanxin Bundle

DeepBlue Bastion (深蓝堡垒) team coordinator skill. Analyzes code quality, security, architecture, and coordinates expert agents (Atlas, Aegis, Ockham, BugHunter, Turbo, Pragmatic) dynamically using both sequential and parallel execution. Use when user needs code review, security audit, architecture assessment, code cleanup, performance optimization, feasibility evaluation, or legacy system maintenance requiring multi-expert collaboration, or any other code quality tasks.

llopresto87 Skill

The authoring discipline for the project's plan-of-record at docs/graph/plans/grill.md — what a worker filling any section carries, and the audit that says whether the plan is still consistent with the specs, the wiki, and the decisions. Use whenever a brief produces or updates grill.md, or grill.md needs a consistency pass. The pass itself (which section, which owner, in which order) is protocol.grill; this skill is how each section is written well.

microsoft Skill

Step-by-step checklist for bumping the pinned ONNX dependency / opset in ONNX Runtime (e.g. ONNX 1.21 / opset 26 → 1.22 / opset 27). Use when integrating a new ONNX release or release-candidate, updating the cmake/deps.txt onnx pin or the cmake/external/onnx submodule, regenerating cmake/patches/onnx/onnx.patch, raising kMaxSupportedOpset, or adding a new opset's CPU kernels. Covers the file taxonomy, archive-hash procedures, patch rebase/mirror rules, the RC→formal strategy, and the optimizer/EP gotchas that the automated audit script misses.

microsoft Skill

When reviewing or fixing Python code that uses setattr() with user-controlled kwargs to configure C++ extension objects (SessionOptions, RunOptions, etc.) in ONNX Runtime. Use this to apply the allowlist pattern that prevents arbitrary file writes and other attacks via reflected property access.

mohitmishra786 Bundle

security-threat-guide skill for security threat modeling and attack surface analysis. Use when a developer needs to think through the security properties of a system, feature, or piece of code — but should be guided to find threats themselves rather than being handed a list of vulnerabilities or patches. Activates on "is this secure?", "what are the security concerns here?", "how could this be attacked?", or any request to assess security posture.

ndisisnd Bundle

Supabase platform standards — Row-Level Security, publishable/anon and secret/service_role key boundaries, Postgres and Edge functions, Storage, Realtime, and the CLI migration workflow. Use when working with RLS policies, Supabase clients, Edge Functions, or supabase/ migrations. Loads alongside the database (Postgres) domain.

ndisisnd Bundle

TypeScript 5.x language standards for type safety, narrowing, generics, modules, and async code. Use for TypeScript implementation or review work; load refs only for tooling, testing, or security-specific tasks.

nekomangaorg Skill

Performs rigorous, adversarial senior-staff code reviews that ruthlessly uncover architectural anti-patterns, edge cases, lifecycle hazards, memory leaks, type-safety gaps, and performance pitfalls. Use this skill when the user asks for a senior developer review, an adversarial code audit, or wants to find every hidden flaw and edge case in a PR or git diff.

nekomangaorg Bundle

Removes app bloat, secures data, and ensures failures are visible. Use this skill to safely eliminate dead code or unused resources, secure vulnerabilities like hardcoded API keys, fix silent exceptions (empty catch blocks), convert heavy assets to WebP, and ensure logs do not contain PII.

auditmos Bundle

Audits Solidity concentrated liquidity manager (CLM) protocols for vulnerabilities including forced unfavorable liquidity deployment via missing TWAP checks, owner rug-pull via TWAP parameter manipulation, tokens permanently stuck from rounding errors, stale token approvals after router updates, and retrospective fee application on previously earned rewards (project)

auditmos Bundle

Audits Solidity oracle integrations for vulnerabilities including missing stale price checks against heartbeat intervals, missing L2 sequencer uptime validation, same heartbeat for multiple feeds, assuming oracle precision, incorrect price feed addresses, unhandled oracle reverts, unhandled depeg events, oracle min/max price issues during flash crashes, using manipulable slot0 prices, price feed direction confusion, and missing circuit breaker checks (project)

auditmos Bundle

Audits Solidity auction mechanisms for manipulation vulnerabilities including self-bidding to reset auction timer, auction start during L2 sequencer downtime affecting timing fairness, insufficient auction length validation allowing very short auctions for immediate seizure, and off-by-one errors allowing seizure during active auction period (project)

auditmos Bundle

Audits Solidity lending and borrowing protocols for vulnerabilities including premature liquidation before default, collateral manipulation preventing liquidation, loan closure without repayment, asymmetric pause mechanisms, token disallowance blocking operations, missing grace periods, incorrect liquidation share calculations, repayments to zero address, forced loan assignments, loan state manipulation via refinancing, double debt accounting, and dust loan griefing attacks

auditmos Bundle

Audits Solidity staking and reward protocols for vulnerabilities including front-running first deposit to steal initial rewards, reward dilution via direct transfers, precision loss in reward calculations causing rounding to zero, flash deposit/withdraw griefing diluting rewards, update not called after reward distribution causing stale index, and balance caching issues during claims (project)

auditmos Bundle

Audits Solidity DEX integrations and smart contracts for slippage vulnerabilities enabling sandwich attacks including zero/missing minAmountOut parameters, block.timestamp or missing deadlines, on-chain slippage calculation via manipulable quoters, multi-hop swaps without final output protection, decimal precision mismatches between token pairs, hard-coded slippage preventing withdrawals during volatility, and fixed fee tier assumptions breaking when liquidity migrates

auditmos Bundle

Audits Solidity smart contracts for signature-related vulnerabilities including missing nonce replay protection allowing signatures to be reused after state changes, cross-chain replay attacks without chain_id validation, missing critical parameters in signed messages enabling manipulation, signatures without expiration timestamps granting lifetime access, unchecked ecrecover return values allowing invalid signatures, and signature malleability via elliptic curve symmetry

auditmos Bundle

Audits Solidity smart contracts for reentrancy vulnerabilities including token transfer reentrancy via ERC777/callback tokens, state updates after external calls enabling draining, cross-function reentrancy manipulating shared state, and read-only reentrancy exploiting stale state during callbacks (project)

auditmos Bundle

Audits Solidity liquidation mechanisms for incentive structure vulnerabilities including missing liquidation rewards making trustless liquidation unprofitable, insufficient incentives for small positions causing bad debt accumulation, profitable users withdrawing collateral eliminating liquidation incentive, missing bad debt handling mechanisms, partial liquidation bypassing bad debt accounting, and lack of partial liquidation preventing whale position liquidations

auditmos Bundle

Audits Solidity smart contracts for arithmetic precision vulnerabilities including division-before-multiplication causing value loss, small amounts rounding to zero enabling fee bypass, token decimal mismatches in multi-asset pools, unsafe downcasts truncating storage values, incorrect rounding direction leaking protocol fees, inverted oracle price pairs, hardcoded decimal assumptions, and time unit confusion in interest calculations

auditmos Bundle

Audits Solidity liquidation mechanisms for denial of service vulnerabilities including unbounded loops over positions causing out-of-gas reverts, data structure corruption preventing liquidation, front-running to block liquidation via nonce changes or self-liquidation, pending withdrawals forcing reverts, malicious ERC721/ERC20 callback reverts, collateral in external vaults not seized, insufficient insurance fund blocking liquidation, fixed bonus exceeding available collateral, incorrect decimal handling, conflicting nonReentrant modifiers, zero value transfer reverts, token deny list issues, and single borrower edge cases

auditmos Bundle

Audits Solidity smart contracts for state validation vulnerabilities including unchecked 2-step ownership transfers allowing address(0) bricking, functions accepting unexpected matching or empty inputs bypassing validation, unchecked return values causing silent failures, non-existent ID manipulation corrupting state, missing access control on critical functions, inconsistent array length validation, and improper pause mechanism implementation

auditmos Bundle

Audits Solidity liquidation mechanisms for unfair liquidation vulnerabilities including missing L2 sequencer grace periods, interest accumulation while paused, repayment paused while liquidation active, late interest/fee updates, lost positive PNL/yield during liquidation, unhealthier post-liquidation state from cherry-picking, corrupted collateral priority, borrower replacement misattribution, no LTV gap allowing immediate liquidation, interest during auctions, and no liquidation slippage protection (project)