본문으로 건너뛰기
cccskills
무료GitHub에 공개

review-security-structure

Review owned or authorized code for security using structure-first evidence: AST/structure maps, call graphs, complexity, Source/Sink flow, and defensive findings. Use when asked for security review, vulnerability review, AST structure map review, SAST triage, Source/Sink, taint flow, parser/scanner hardening, CI/CD security, LLM/agent tool boundary review, 脆弱性レビュー, 構造マップ, セキュリティレビュー.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

연동 도구Qiita
설치 방법 보기

포함된 파일(4)

  • SKILL.md5.6 KB
  • LICENSE.txt5.2 KB
  • references/output-format.md1.8 KB
  • references/structure-map.md2.3 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Review Security Structure

Defensively review code or structure artifacts by reading architecture and data flow before reading full source. Use structural signals to identify vulnerabilities, logic flaws, parser/scanner risks, CI/CD risks, and LLM/agent tool-boundary risks.

When to Use

  • security review, vulnerability review, SAST triage, AST, structure map, call graph, Source/Sink, taint flow
  • 脆弱性レビュー, セキュリティレビュー, 構造マップ, AST レポート, 依存関係, 複雑度
  • Reviewing owned or explicitly authorized code, design docs, scan results, or generated structure maps
  • Hardening parsers, scanners, CI/CD tools, file walkers, and agent/tool-call boundaries against malformed or adversarial input

Safety Scope

  • Keep the work defensive: review, risk explanation, safe verification ideas, and minimal fixes.
  • Do not provide unauthorized testing, intrusion, persistence, evasion, credential theft, weaponized PoC, or destructive external steps.
  • If exploitability is uncertain, place the item in Hypotheses rather than Findings.
  • If code changes are requested, keep them minimal and verify with existing tests or a focused local check.

Inputs to Prefer

Use provided structure artifacts first, then inspect the smallest code/config range needed.

InputExamples
StructureAST summaries, class/function lists, Mermaid graphs, JSON reports
Data flowSource, Propagator, Sanitizer, Sink, taint flow
Call graphcaller -> callee edges, boundary-crossing calls, fallback paths
Complexitylarge functions, branch concentration, exception density
Scope/statevariable scope, global state, shared mutable state, auth boundaries
Static resultssecret scan, dependency scan, lint/type/SAST warnings
ContextREADME, design notes, CI workflow, deployment config

Structure Map Build

同等の成果物がない場合は、findings review に入る前に最小で read-only の structure map を作る。手順(7 steps)と minimum map contract (entry_points / files / symbols / imports / call_edges / complexity / sources / sinks / sanitizers / scan_limits) は references/structure-map.md。生成ができない場合は Structure Map Summary に blocker と limits を記録する。

Review Flow

  1. Gate the target: assume review is allowed for current workspace/user-provided artifacts; ask only if ownership or authorization is unclear.
  2. Classify the target: web app, CLI, library, scanner, CI/CD tool, infrastructure definition, data processor, extension, or agent tool.
  3. Read an existing structure map, or build the minimal map from the contract above before full source reading.
  4. Model trust boundaries: who controls which input, where it flows, what authority the Sink has, and what data is sensitive.
  5. Trace Source -> Propagator -> Sanitizer -> Sink. Look for missing validation, wrong order, branch gaps, implicit deserialization, and type-conversion surprises.
  6. Review call graph paths that bypass authn/authz, validation, initialization, feature flags, or normal handlers.
  7. Review complexity and logic risks: giant functions, broad try/catch, deep nesting, fallback behavior, shared state, TOCTOU, and cache races.
  8. For parsers/scanners/file walkers, prioritize crash, unbounded recursion, symlink loops, huge/deep ASTs, encoding edge cases, dependency resolution failures, and detection bypass.
  9. For CI/CD, review workflow inputs, artifact/cache trust, token permissions, PR boundaries, release gates, and secret exposure.
  10. For LLM/agent code, review prompt injection paths, external document trust, tool-call authorization, path safety, command policy, and log redaction.

Evidence Rules

  • Findings require structural signal, reachability, impact, and a defensive verification or fix direction.
  • Confidence is High, Medium, or Low. Avoid certainty language unless verified.
  • Keep unsupported ideas in Hypotheses with the missing evidence and next check.
  • Reference local files with precise paths and line links when possible. Do not paste full source files.

Output Format

Findings -> Structure Map Summary -> Hypotheses -> Code to Inspect -> Recommended Fix Plan -> Verification Summary の順で返す。全テーブルスキーマと Recommended Fix Plan 本文は references/output-format.md。Findings がゼロの場合はその旨を先頭に明示する。

Thanks to / References

Inspired by these structure-first review resources. Treat them as references, not required dependencies.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Design, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or hook before escalating to multi-agent design. Use for .agent.md / .instructions.md / .prompt.md / AGENTS.md work, workflow architecture, orchestration planning, scheduled automation model allocation, or when agent workflows may be overkill. Triggers on 'agent workflow', 'create agent', 'automation models', 'ワークフロー設計', 'orchestrator'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

Design, run, and review fair performance, token, and cost comparisons across GitHub Copilot CLI, Codex CLI, and direct model APIs. Use for AI CLI benchmark, Copilot vs Codex, prompt-cache diagnosis, cache read/write analysis, fresh-process latency measurement, token-cost comparison, or when a benchmark must separate provider caching from local CLI caches.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

Analyze historical VS Code GitHub Copilot Chat sessions by model, reasoning effort, AIU, time, reliability, workflow behavior, and external quality evidence, or safely prune workspace-scoped local chat history by age. Use for session analysis, repeated-task retrospectives, model evaluation, cost/performance analysis, and old session cleanup.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

Create reproducible animated infographic GIFs from structured data or measured results, with audience-language labels, explicit timing semantics, representative-frame QA, and a static fallback. Use when asked for GIF生成, animated infographic, 動的インフォグラフィック, 結果が流れる図, animated benchmark, or a blog/SNS animation whose displayed metrics must remain traceable to source data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

archify

무료

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid. Also use for Archify, interactive or animated HTML diagrams, インタラクティブ図, 動く構成図. When an editable .drawio file is required, use the draw.io workflow instead and treat Archify HTML only as a supplement.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

Generate ASCII-art text banners for terminals, READMEs, and CLI startup messages. Use when a user asks for an ASCII banner, text art, バナー, アスキーアート, or a decorative header for a script/README.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

aktsmm의 스킬 모두 보기

이 스킬의 문제 신고