Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sangrokjung/claude-forge --skill security-pipelinegit clone --depth 1 https://github.com/sangrokjung/claude-forgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sangrokjung/claude-forge/security-pipeline)<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/security-pipeline"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/security-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/security-pipeline"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/security-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 67 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.01386 |
| Opus 5.5 | $0.00019 | $0.00554 |
| Sonnet 5.5 | $0.00010 | $0.00277 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
security-pipeline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
보안 파이프라인 스킬은 코드 변경 시 자동으로 CWE Top 25 기반 보안 검증을 수행한다.
/handoff-verify --security, /commit-push-pr 실행 시 통합 동작한다.
보안 체크리스트 참조: ~/.claude/skills/_reference/security-checklist.md
effort:max가 항상 강제 적용된다. 보안 검증은 축약하지 않는다.
Trigger Conditions
파일 패턴 기반 자동 트리거
다음 패턴을 포함하는 파일이 변경되면 보안 파이프라인이 자동으로 실행된다:
| 패턴 | 트리거 수준 | 설명 |
|---|---|---|
**/auth/** |
Full Scan | 인증 관련 모듈 |
**/payment/** |
Full Scan | 결제 처리 모듈 |
**/api/** |
CWE Scan | API 엔드포인트 |
**/middleware/** |
CWE Scan | 미들웨어 |
**/session* |
CWE Scan | 세션 관리 |
**/token* |
CWE Scan | 토큰 처리 |
**/crypto* |
CWE Scan | 암호화 로직 |
**/admin/** |
Full + STRIDE | 관리자 기능 |
**/upload* |
CWE Scan | 파일 업로드 |
**/.env* |
Credential Scan | 환경변수 파일 |
**/config/secret* |
Credential Scan | 시크릿 설정 |
커밋 기반 자동 트리거
/commit-push-pr 실행 시 staged 파일 목록에서 위 패턴이 감지되면,
커밋 전 보안 파이프라인이 자동으로 실행된다.
CWE Scanning Rules
Critical (커밋 차단)
| CWE ID | Rule | Grep Pattern |
|---|---|---|
| CWE-89 | SQL Injection | query\(.*\$\{, query\(.*\+ |
| CWE-79 | XSS | innerHTML, dangerouslySetInnerHTML, v-html |
| CWE-78 | OS Command Injection | exec\(.*\$\{, spawn\(.*req\. |
| CWE-77 | Command Injection | Template string in shell command |
| CWE-798 | Hardcoded Credentials | apiKey\s*=\s*['"], secret\s*=\s*['"] |
High (경고, 커밋 허용)
| CWE ID | Rule | Grep Pattern |
|---|---|---|
| CWE-22 | Path Traversal | \.\.\/ with user input |
| CWE-352 | CSRF | POST handler without csrf check |
| CWE-287 | Improper Auth | Route without auth middleware |
| CWE-862 | Missing Authz | Handler without role/permission check |
| CWE-502 | Unsafe Deserialization | eval\(, new Function\( |
| CWE-918 | SSRF | fetch\(.*req\., axios.*req\. |
| CWE-434 | Unrestricted Upload | Upload without validation |
| CWE-269 | Privilege Escalation | Role change without verification |
Medium (정보 제공)
| CWE ID | Rule | Grep Pattern |
|---|---|---|
| CWE-200 | Info Disclosure | console\.log.*password|token|secret |
| CWE-20 | Input Validation | Endpoint without schema validation |
| CWE-327 | Broken Crypto | md5\(, sha1\(, Math\.random\(\) |
| CWE-276 | Incorrect Perms | origin:\s*['"]?\*, 0o?777 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 154 lines · 48 tokens per session scan A 04b93f720d59
security-pipeline is a skill published in the GitHub repository sangrokjung/claude-forge (863 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,386 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
git-commit
Safely create a git commit by validating repository state, staging intended changes, scanning for secrets/conflicts, generating a Conventional Commits message (repository convention first, else an English Angular default) from the staged diff, and committing without amend.
inbox-triage
Daily GitHub notification inbox triage - surfaces aging vuln PR replies, security advisories, review requests, and mentions that need action.
install-skill
Install a community skill pack into this fork from a GitHub repo and ship it as an auto-merged PR.
repo-stats-autoupdate
Keeps README badge + inline counts in sync with the real number of skills, agents, graph nodes/edges, communities, converted pipelines, and test inventory. Runs automatically on every commit via a git pre-commit hook. Use when the README drifts from reality or before publishing a release.
core-workflow
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, review-based validation, and communication standards.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.