safe-webSecurely fetch and search web content by scanning and blocking prompt injection threats using PromptGuard before returning results.
Install via ClawdBot CLI:
clawdbot install adamnaghs/safe-webGrade 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 previous instructions"Calls external URL not in known-safe list
https://clawhub.ai/seojoonkim/prompt-guardUses known external API (expected, informational)
api.search.brave.comAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Researchers use safe-web to securely fetch and scan academic papers or articles from various online repositories, ensuring that no hidden prompt injections compromise their AI-assisted analysis tools. This is critical when aggregating data from less-trusted sources for literature reviews or meta-analyses.
Financial analysts employ safe-web to search and fetch real-time news articles about stock markets or economic trends, scanning for malicious content that could manipulate AI-driven trading algorithms. This prevents injection attacks that might alter investment decisions based on falsified data.
Medical professionals use safe-web to securely access and scan web-based health guidelines or research studies, protecting AI diagnostic tools from prompt injections that could lead to incorrect medical advice. This ensures patient safety when integrating external health data into clinical workflows.
Security teams utilize safe-web to fetch and scan reports from threat intelligence feeds or forums, safeguarding their AI systems from hidden injections that might compromise security analyses. This helps in maintaining the integrity of automated threat detection and response processes.
E-commerce platforms use safe-web to fetch product descriptions and reviews from competitor websites, scanning for injection attempts that could skew AI-powered pricing or recommendation engines. This ensures accurate data collection without security risks in dynamic market environments.
Offer safe-web as a premium subscription for businesses, providing regular updates, priority support, and enhanced scanning features. Revenue is generated through monthly or annual fees, targeting enterprises that require continuous web content security for their AI operations.
Provide a free version of safe-web for basic usage, with paid tiers offering advanced features like higher API limits, custom scanning rules, and integration support. Revenue comes from API usage fees and premium upgrades, appealing to developers and small to medium-sized businesses.
Sell enterprise licenses that include custom integrations, dedicated support, and tailored security configurations for large organizations. Revenue is generated through one-time licensing fees or annual contracts, focusing on industries with strict compliance and security needs.
💬 Integration Tip
Ensure PromptGuard is correctly installed in the workspace and set the BRAVE_API_KEY environment variable for search functionality to enable secure web queries.
Scored Jun 19, 2026
Manage and operate ClawSec Monitor v3.0, a MITM HTTP/HTTPS proxy that logs AI agent traffic, detects exfiltration and injection threats in real time.
Command-line security analyzer for ClawHub skills. Run analyze-skill.sh to scan SKILL.md files for malicious patterns, credential leaks, and C2 infrastructure before installation. Includes threat intelligence database with 20+ detection patterns.
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them. Security audit tool that detects data exfiltration, system modification attempts, backdoors, and obfuscation techniques.
577+ pattern prompt injection defense. Now with typo-tolerant bypass detection. TieredPatternLoader fully operational. Drop-in defense for any LLM application.
Security scanner for ClawHub skills. Vet third-party skills before installation — detect dangerous patterns, suspicious code, and risky dependencies.
Security audit and hardening for AI agents — credential hygiene, secret scanning, prompt injection defense, data leakage prevention, and privacy zones.