Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

minduploadedcrab-skillguard

bởi minduploadedcrab

Coding Agents & IDEs
381Lượt 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

Security scanner for OpenClaw skills.

Mô tả

Kỹ năng này làm gì

SkillGuard scans OpenClaw skill directories for security threats before installation. It detects credential theft, data exfiltration, prompt injection, obfuscation, and permission overreach. Produces a risk score and verdict for each scanned skill.

Generic antivirus misses agent-specific attack vectors like prompt injection and symlink escapes that SkillGuard is built to catch.

Khi nào nên dùng

  • Scanning a third-party skill before installing it
  • Auditing all currently installed skills for backdoors
  • Checking a skill for hardcoded API keys or secrets
  • Detecting prompt injection hidden in a skill's SKILL.md
  • Reviewing dependency scripts for malicious post-install hooks

Quy trình ví dụ

ĐẦU VÀO

User asks: scan the skill at ~/.openclaw/workspace/skills/some-skill before I install it

AGENT
  1. 1

    Runs python3 scripts/skillguard.py scan ~/.openclaw/workspace/skills/some-skill --json

  2. 2

    Parses the JSON output for risk score, verdict, and findings

  3. 3

    Checks for FAIL or WARN verdicts and surfaces specific findings with severity

  4. 4

    Reports credential access or network exfiltration detections if present

  5. 5

    Presents the final verdict and recommends whether to proceed with installation

ĐẦU RA

Risk Score: 42/100, Verdict: WARN — one finding: outbound HTTP call to unrecognized domain in index.js line 14

Cài đặt

clawhub install minduploadedcrab/minduploadedcrab-skillguard

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

Liên kết