eli-prompt-guardAutomatically detects and blocks prompt injection attempts across multiple platforms to protect against unauthorized commands and data leaks.
Install via ClawdBot CLI:
clawdbot install danlct27/eli-prompt-guardGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"ignore all previous instructions"Sends data to undocumented external endpoint (potential exfiltration)
post → https://evil.com/hookPotentially destructive shell commands in tool definitions
rm -rf /Calls external URL not in known-safe list
https://evil.com/hookGenerated May 23, 2026
An AI agent automatically drafts and posts content to platforms like Twitter and LinkedIn. Prompt Guard scans the content for injection attacks, preventing malicious instructions from hijacking the post or leaking sensitive data.
An e-commerce platform uses an AI agent to submit product data to external APIs for price comparison. Prompt Guard checks for injection attempts in product descriptions or user reviews before submission, preventing data exfiltration or system takeover.
A customer support chatbot processes user messages that might contain attempts to trick the system into revealing API keys or passwords. Prompt Guard detects and blocks such attempts, ensuring sensitive information stays secure.
A fintech app auto-fills and submits loan application forms to external banks. Prompt Guard inspects the submitted data for injection patterns, preventing malicious code or instructions from being sent to financial systems.
An AI agent writes generated reports to files that are later shared publicly. Prompt Guard scans the content for any embedded injection attacks (e.g., hidden instructions) before finalizing the file write, protecting downstream users.
Offer Prompt Guard as a premium security add-on for existing AI agent platforms. Charge a monthly subscription per user or per request volume, providing critical protection against prompt injection in automated workflows.
License the Prompt Guard regex-based detection engine as an API for enterprises to integrate into their own AI systems. Revenue comes from per-API-call pricing or annual enterprise licenses.
Provide consulting services to customize Prompt Guard rules for specific industries (e.g., healthcare, finance) and integrate into existing compliance workflows. Revenue from project-based fees and recurring support contracts.
💬 Integration Tip
Integrate Prompt Guard as a middleware function called before any external submission to check content; leverage the pre-built regex patterns for quick deployment.
Scored Jun 29, 2026
AI Analysis
This skill is a defensive security control designed to detect and prevent prompt injection attacks. It does not send user data to external servers, contains no hidden instructions to override safety, and its purpose is purely protective. The rule-based signals found are examples of what the skill is designed to detect, not actions the skill itself performs.
Audited Apr 18, 2026 · audit v1.0
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Security scanner for AI agent skills. 9 built-in detection signatures. Identifies secrets, unsafe execution patterns, and prompt injection. Sub-50ms results.
Wallet anti-theft guard. One-click scan for high-risk wallet approvals to protect user assets. Use when a user asks for a wallet security check, wallet healt...
Comprehensive security audit for an agent's full skill stack. Chains scanner, differ, trust-verifier, and health-monitor into a single assessment with priori...
GEO Audit — AI Search Visibility Checker for ChatGPT, Perplexity, Claude & Gemini. 29-point GEO readiness checklist: robots.txt AI crawler access, Index...
Audit and analyze Solidity smart contracts for security vulnerabilities. Use when reviewing, auditing, or analyzing smart contracts, Solidity code, DeFi prot...