Keyword: tool-poisoning

vigile-scan
Released
19h ago
Version
3.0.1
Security scanner for AI agent tools — detect tool poisoning, permission abuse, and supply chain attacks in MCP servers and agent skills
mcp security ai-agent scanner trust model-context-protocol +9
@fernforge/mcp-conform
Released
yesterday
Version
0.1.0
Author-side pre-publish conformance & safety linter for MCP (Model Context Protocol) servers — eslint for your MCP server. Checks tool annotations, schema hygiene, tool-poisoning/injection patterns, and registry/distribution metadata before you publish. C
mcp model-context-protocol modelcontextprotocol lint linter conformance +9
@wasmagent/mcp-firewall
Released
2d ago
Version
1.3.4
Runtime firewall for MCP and tool-augmented agents — descriptor integrity, static vetting, per-call policy, taint tracking, consent ledger
wasmagent mcp firewall security tool-poisoning rug-pull +3
mcp-security-scanner
Released
3d ago
Version
1.1.1
MCP security scanner — 55 tools for runtime inspection, static analysis, config audit, dependency analysis. OWASP MCP Top 10 compliance. OAuth, TLS, fuzz testing, prompt injection, tool mutation detection. 100% local, zero external API calls.
mcp model-context-protocol security scanner static-analysis sast +14