कंटेंट पर जाएँ
TakoAPI
स्किल्स पर वापस

aegis-shield

deegerwalker द्वारा

Web & Frontend Development
688clawskills.sh द्वारा बताए गए डाउनलोड
0व्यूज़
0 लाइकइस स्किल को लाइक करने के लिए साइन इन करें
—अभी तक कोई रेटिंग नहीं
आपकी रेटिंग

संक्षिप्त

Prompt-injection and data-exfiltration screening for untrusted text.

विवरण

यह स्किल क्या करती है

Screens untrusted text for prompt injection, data exfiltration, and tool-abuse patterns before it reaches memory or other tools. Assigns a severity score and routes content to either acceptance or quarantine. Includes a safe memory append workflow that enforces scan and lint checks before any write.

Intercepts malicious content at the boundary rather than relying on downstream tools to handle hostile input safely.

इसे कब इस्तेमाल करें

  • Scanning email content before summarizing it to an agent
  • Screening scraped web pages before feeding them into a pipeline
  • Quarantining social media replies that contain suspicious instructions
  • Enforcing sanitized memory writes when processing user-supplied input
  • Blocking exfiltration attempts hidden in LLM-targeted document payloads

उदाहरण वर्कफ़्लो

इनपुट

User asks: scan this webpage content before summarizing it

एजेंट
  1. 1

    Pass the raw fetched text to the scan step

  2. 2

    Receive severity score and flag list from the scanner

  3. 3

    Check if severity is medium or higher

  4. 4

    If severity is medium+, route content to quarantine and halt pipeline

  5. 5

    If severity is low, proceed to summarize the sanitized text

आउटपुट

Content is either quarantined with a report or cleared for downstream use

इंस्टॉलेशन

clawhub install deegerwalker/aegis-shield

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

लिंक