🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI
alphaparkinc/genpark-realtime-storefront-hero-personalization-engine-skillReal-time storefront hero banner & copy personalization engine (Dynamic Yield)
alphaparkinc/genpark-pre-purchase-return-fraud-propensity-scorer-skillPre-purchase return fraud propensity & wardrobing scorer (Gorgias / Yotpo)
Alpha-Park/genpark-split-shipment-warehouse-distance-minimizer-skill3PL fulfillment warehouse distance & split-shipment minimizer (Flexport / ShipBob)
Alpha-Park/genpark-realtime-storefront-hero-personalization-engine-skillReal-time storefront hero banner & copy personalization engine (Dynamic Yield)
alphaparkinc/genpark-split-shipment-warehouse-distance-minimizer-skill3PL fulfillment warehouse distance & split-shipment minimizer (Flexport / ShipBob)
alphaparkinc/genpark-multi-touch-ad-attribution-shapley-resolver-skillMulti-touch ad attribution Shapley value & ROAS contribution resolver (Triple Whale)
Alpha-Park/genpark-multi-touch-ad-attribution-shapley-resolver-skillMulti-touch ad attribution Shapley value & ROAS contribution resolver (Triple Whale)
alphaparkinc/genpark-predictive-ltv-churn-reengagement-trigger-skillPredictive customer lifetime value (pLTV) churn re-engagement trigger (Klaviyo)
Alpha-Park/genpark-pre-purchase-return-fraud-propensity-scorer-skillPre-purchase return fraud propensity & wardrobing scorer (Gorgias / Yotpo)
chawdamrunal/assayMCP & Claude Code security scanner — threat-models plugins, MCP servers, hooks, skills & connectors with an LLM before you trust them. Catches prompt injection, tool poisoning & credential exfiltratio
proluct/skannaSecurity scanner for Claude Code skills, plugins, and MCP servers. A verdict before you install.
davidnichols-ops/trustcardCryptographic trust infrastructure for MCP servers — signed manifests, TOFU pinning, two-gate enforcement, and the "npm audit" scanner.
eltociear/mcp-auditScan MCP servers & AI-agent skills for malicious patterns (prompt injection in tool descriptions, credential exfil, download-and-execute). 17 patterns / 60 signatures, zero-dep. Measured over 196 publ
Paraphern/rugsnareRuntime integrity gateway for AI agents: pin MCP tool descriptions, snare rug-pulls and drift, verify releases on-chain. Zero-dep.