All projects on Base matching “agent-skills”

Pre-install scan of an npm or PyPI package, GitHub repo, raw URL, ClawHub skill, MCP server or tool list, or inline content. Matches OSV and OpenSSF malicious-package advisories, then behavioral analysis for credential theft, exfiltration, obfuscation, prompt injection, install-time droppers and MCP tool poisoning. Returns a verdict, file-and-line evidence, a SHA-256 of the input and an Ed25519-si

MCP Server Scan by Agentropolis: scan a live remote MCP server URL (or pasted tools/list) before your agent connects. Reads initialize + tools/list only, never calls a tool. Flags poisoned or hidden tool instructions (IMPORTANT tags, conceal-from-user, secret or side-channel asks, invisible Unicode, tool shadowing, payment injection). Fingerprints every tool (sha256) and diffs vs your last scan to