Webclaw
Web extraction engine for LLMs using TLS fingerprinting to bypass bot detection, output as markdown.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Webclaw, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.
Overview
Webclaw is a web-extraction engine for LLMs that uses TLS fingerprinting to evade bot detection and returns clean markdown for agent consumption. It fetches pages from arbitrary URLs. Bot-detection evasion is a dual-use capability, and the returned page content is untrusted input that can carry prompt injection.
Key features
- TLS-fingerprint bot evasion
- Clean markdown output
- LLM-optimized extraction
- Arbitrary URL fetching
Use cases
- Extracting content from protected sites
- Feeding web content to LLMs
- Agentic research