Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

scan-skill

bởi itsnishi

PDF & Documents
1.1kLượt 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

Deep security analysis of an individual skill before installation.

Mô tả

Kỹ năng này làm gì

Analyzes a skill directory for security vulnerabilities before installation. Detects injection techniques, obfuscation, malicious shell patterns, and instruction override attempts. Produces a severity-ranked report with per-finding recommendations.

Runs a comprehensive set of AI-agent-specific checks in one pass rather than manually reading each skill file for subtle injection or obfuscation.

Khi nào nên dùng

  • Vetting a third-party skill before adding it to your agent config
  • Reviewing a skill submitted by an external contributor
  • Auditing skills pulled from a public marketplace
  • Checking for hidden instructions or encoded payloads in downloaded skills
  • Pre-installation security gate in a team review workflow

Quy trình ví dụ

ĐẦU VÀO

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

AGENT
  1. 1

    Receives the target skill directory path as the argument

  2. 2

    Runs scan_skill.py against the specified directory

  3. 3

    Analyzes SKILL.md frontmatter for dangerous field combinations and hidden skills

  4. 4

    Checks scripts/ contents for remote-code-pipe-to-shell patterns, encoded payloads, and executable permissions

  5. 5

    Scans for zero-width characters, base64/hex obfuscation, and instruction override attempts

ĐẦU RA

Structured report listing findings by severity with specific recommendations for each issue found

Cài đặt

clawhub install itsnishi/scan-skill

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

Liên kết