Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

vet-repo

bởi itsnishi

PDF & Documents
907Lượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Scan repository agent configuration files for known malicious patterns.

Mô tả

Kỹ năng này làm gì

Scans a repository's agent configuration files for known malicious patterns before you trust or run its configurations. Checks Claude settings, skill files, MCP configs, and project instruction files. Outputs a severity-grouped report with recommendations.

Catches agent-level attack vectors like hook auto-approval, hidden curl|bash chains, and instruction injection that standard code review tools don't check for.

Khi nào nên dùng

  • Auditing a cloned open-source repo before running its agent setup
  • Reviewing a contractor's codebase for injected agent instructions
  • Checking for malicious hooks after a pull request modifies .claude/
  • Security review before onboarding a new project with MCP integrations
  • Catching prompt injection attempts hidden in CLAUDE.md files

Quy trình ví dụ

ĐẦU VÀO

User asks: scan this repo for malicious agent configs before I start working in it

AGENT
  1. 1

    Resolves SKILL_DIR and PROJECT_ROOT paths

  2. 2

    Runs vet_repo.py against the project root

  3. 3

    Scans .claude/settings.json for dangerous hook configs

  4. 4

    Scans .claude/skills/, .mcp.json, and CLAUDE.md for injection patterns

  5. 5

    Groups findings by severity and generates recommendations

ĐẦU RA

Structured report listing CRITICAL/HIGH/MEDIUM/LOW/INFO findings across all agent config files, with actionable remediation steps for each issue

Cài đặt

clawhub install itsnishi/vet-repo

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết