Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

mayguard

bởi balkanblbn

Coding Agents & IDEs
389Lượt tải do clawskills.sh công bố
1Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

A security auditor for agent skills.

Mô tả

Kỹ năng này làm gì

Static analysis tool that scans agent skill directories for security threats before installation. Detects credential theft patterns, suspicious network calls, destructive commands, and code obfuscation. Returns a safety rating (SAFE, CAUTION, SUSPICIOUS, or DANGEROUS) with specific findings per file.

Catches attack patterns specific to agent skill architectures, like env file exfiltration and eval-based obfuscation, that general-purpose linters miss.

Khi nào nên dùng

  • Auditing a downloaded skill before moving it to the active skills folder
  • Detecting hardcoded API keys or env file access in third-party skills
  • Identifying outbound webhook or tunnel calls in untrusted skill code
  • Scanning community-shared skills before running them locally
  • Checking for privilege escalation or destructive commands in a new skill

Quy trình ví dụ

ĐẦU VÀO

User asks: Audit the skill I downloaded to ~/Downloads/new-skill before I install it

AGENT
  1. 1

    Run python3 scripts/audit.py ~/Downloads/new-skill against the target directory

  2. 2

    Scan source files for credential access patterns including .env and SSH key references

  3. 3

    Check for suspicious network calls such as webhook endpoints and ngrok or localtunnel usage

  4. 4

    Detect obfuscation techniques including eval, exec, and base64 decoding

  5. 5

    Compute a numerical risk score and assign an overall safety rating

ĐẦU RA

Report showing status CAUTION, risk score, and a list of flagged patterns with the specific files and lines that triggered each warning

Cài đặt

clawhub install balkanblbn/mayguard

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

Liên kết