कंटेंट पर जाएँ
TakoAPI
स्किल्स पर वापस

clawdefender

nukewire द्वारा

Clawdbot Tools
7.0kclawskills.sh द्वारा बताए गए डाउनलोड
29स्टार
1व्यूज़
0 लाइकइस स्किल को लाइक करने के लिए साइन इन करें
—अभी तक कोई रेटिंग नहीं
आपकी रेटिंग

संक्षिप्त

Security scanner and input sanitizer for AI agents.

विवरण

यह स्किल क्या करती है

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.

इसे कब इस्तेमाल करें

  • 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

उदाहरण वर्कफ़्लो

इनपुट

User asks: sanitize this API response before the agent processes it

एजेंट
  1. 1

    Pipe the API response through sanitize.sh with the --json flag

  2. 2

    Scanner checks content against prompt injection, command injection, and exfiltration patterns

  3. 3

    Flagged sections are wrapped with warning markers and withheld from processing

  4. 4

    Clean content passes through for normal agent use

आउटपुट

Sanitized JSON ready for the agent, with suspicious sections marked and flagged to the user

इंस्टॉलेशन

clawhub install nukewire/clawdefender

CLI कमांड चलाएँ, या प्रॉम्प्ट को Claude Code, Cursor, Codex या जो भी कोडिंग एजेंट आप इस्तेमाल करते हैं उसमें पेस्ट करें।

लिंक