security-guardian
bởi 1999azzar
Coding Agents & IDEsTóm tắt
Automated security auditing for OpenClaw projects.
Mô tả
Kỹ năng này làm gì
Scans project directories for hardcoded secrets (API keys, tokens) and Docker images for CVEs using Trivy. Outputs structured reports with file paths and line numbers. Works alongside mema-vault to move detected secrets into a credential store.
Combines secret detection and container CVE scanning in one workflow, eliminating the need to configure and interpret separate tools for each concern.
Khi nào nên dùng
- Catching leaked API keys before a production push
- Auditing a Docker image for HIGH and CRITICAL CVEs before deployment
- Finding hardcoded tokens in source files during a code review
- Replacing plaintext credentials with vault lookups after detection
- Checking container base images for known vulnerabilities during CI
Quy trình ví dụ
User asks: 'Scan ./src for hardcoded credentials'
- 1
Run scan_secrets.py against the target directory
- 2
Parse the report for findings, noting each file path and line number
- 3
Flag each hardcoded secret as a high-severity finding
- 4
Invoke mema-vault to store the secret securely
- 5
Replace the plaintext value in source code with a vault lookup or environment variable reference
Structured report listing affected files and line numbers, with secrets removed from source and stored in mema-vault
Yêu cầu
- trivy (CLI, installed on host)
- mema-vault skill
Cài đặt
clawhub install 1999azzar/security-guardianChạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.