clawdefender
por nukewire
Clawdbot ToolsResumo
Security scanner and input sanitizer for AI agents.
Descrição
O que esta skill faz
Security scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal across 90+ patterns. Runs as shell scripts that pipe into any agent workflow.
It runs as a standard shell pipe with no external dependencies, so it integrates into any existing agent workflow without additional configuration.
Quando usá-la
- Auditing all installed skills for malware before running them
- Sanitizing API responses before an agent acts on them
- Validating a URL before fetching to prevent SSRF
- Filtering GitHub issue content to block embedded injection attempts
- Blocking credential theft attempts in untrusted email content
Exemplo de fluxo de trabalho
User asks: sanitize this API response before the agent processes it
- 1
Pipe the API response through sanitize.sh with the --json flag
- 2
Scanner checks content against prompt injection, command injection, and exfiltration patterns
- 3
Flagged sections are wrapped with warning markers and withheld from processing
- 4
Clean content passes through for normal agent use
Sanitized JSON ready for the agent, with suspicious sections marked and flagged to the user
Instalação
clawhub install nukewire/clawdefenderExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.