Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

skulk-skill-scanner

bởi adainthelab

Coding Agents & IDEs
472Lượt 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 OpenClaw skill folders for security red flags before installing or publishing.

Mô tả

Kỹ năng này làm gì

Static security scanner for OpenClaw agent skill folders. Analyzes SKILL.md files and associated scripts for data exfiltration, credential theft, prompt injection, obfuscation, and supply chain risks. Produces a scored report with severity-tiered findings and CI-friendly exit codes.

Automated scoring with severity tiers and a CI-friendly exit code makes it faster to gate skill installs than reading every script manually.

Khi nào nên dùng

  • Checking a downloaded skill before enabling it in your agent
  • Auditing your own skill's files before publishing to ClawHub
  • Blocking failing skills in CI pipelines using exit code 1
  • Scanning third-party skills for obfuscated or hidden instructions
  • Running one-line summary checks on a skill collection as a heartbeat

Quy trình ví dụ

ĐẦU VÀO

User asks: Is ./skills/some-skill safe to install?

AGENT
  1. 1

    Runs the scanner against the skill folder with --verbose

  2. 2

    Parses SKILL.md and associated scripts for pattern matches

  3. 3

    Assigns severity levels (critical/high/medium/info) to each finding

  4. 4

    Calculates a 0-100 score based on per-rule deductions

  5. 5

    Returns PASS, WARN, or FAIL with a list of flagged rules and locations

ĐẦU RA

Score 82/100 — PASS. 1 info flag: API key reference in config.js.

Cài đặt

clawhub install adainthelab/skulk-skill-scanner

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

Liên kết