Skip to main content

reviewing-security

Scans a GitHub pull request for security vulnerabilities including OWASP Top 10 issues, hardcoded secrets, and dependency CVEs. Returns a structured JSON findings report. Use when asked to review, audit, or scan a PR for security issues.

소스 정보

저장소
BerriAI/litellm-agent-platform
최근 소스 활동
2026년 5월 15일 20:05
감지된 SKILL.md 언어
영어
스타
542
포크
59

설치 방법

기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.

소스 파일 검토

설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.

SKILL.md 표시 중

SKILL.md
소스 지침 · 읽기 전용 미리보기
name
reviewing-security
description
Scans a GitHub pull request for security vulnerabilities including OWASP Top 10 issues, hardcoded secrets, and dependency CVEs. Returns a structured JSON findings report. Use when asked to review, audit, or scan a PR for security issues.
## PR security scan Copy this checklist and track progress: ``` - [ ] 1. Fetch PR diff - [ ] 2. Secrets scan - [ ] 3. SAST scan - [ ] 4. Dependency audit (if lockfile changed) - [ ] 5. Auth/authz regression check - [ ] 6. Output findings ``` ### Step 1 — Fetch diff ```bash gh pr diff <PR_URL> ``` ### Step 2 — Secrets scan ```bash gitleaks detect --source . --no-git 2>/dev/null; gitleaks_exit=$?; [ $gitleaks_exit -eq 2 ] && echo "gitleaks not available, scanning manually" ``` Note: exit code 1 means findings were detected (expected); exit code 2 means gitleaks could not run. Flag: API keys, tokens, passwords, PII in changed lines. ### Step 3 — SAST scan ```bash semgrep --config=auto --quiet 2>/dev/null; semgrep_exit=$?; [ $semgrep_exit -ge 2 ] && echo "semgrep not available" ``` Note: exit code 1 means findings were detected (expected); exit code 2+ means semgrep could not run. Focus: injection (SQL/cmd/XSS), broken access control, insecure deserialization, crypto misuse. ### Step 4 — Dependency audit Only if `package.json`, `requirements.txt`, `go.mod`, or lockfiles changed: ```bash npm audit --json 2>/dev/null || pip-audit 2>/dev/null || govulncheck ./... 2>/dev/null ``` ### Step 5 — Auth/authz regression Grep for changes to middleware, permission checks, session handling. Flag removed or weakened guards. ### Step 6 — Output ```json { "summary": "<N> critical, <N> high, <N> medium", "findings": [ { "severity": "critical|high|medium|low|info", "type": "secret|injection|auth|dependency|other", "file": "path/to/file.ts", "line": 14, "description": "Specific issue description." } ], "recommendation": "Block merge / Merge with caveats / Safe to merge" } ``` **Rules:** Never approve or merge. Report only. If no issues found, state explicitly with confidence level.
GitHub에서 보기