fittings-npi-provider-lookup

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). One or more links point to a downloadable script (call.mjs) on an external host with explicit instructions to fetch and execute it, which is a common vector for malware and therefore suspicious.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). In the required runtime workflow, the skill npi.provider-lookup performs a direct GET request to https://fittings.sh/v1/npi/provider-lookup using user-supplied query fields (e.g., npi, firstName, lastName, organizationName, etc.), but it does not ingest outsider-authored free text from an external feed or queue without first selecting structured inputs.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs downloading and executing remote code with "curl -sO https://fittings.sh/skill/call.mjs" followed by "node call.mjs", so the URL https://fittings.sh/skill/call.mjs is fetched at runtime and executed.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly describes a paid call flow that requires signing authorizations with an EVM wallet: it instructs setting FITTINGS_PRIVATE_KEY, using a wallet holding USDC on Base, and running a client (call.mjs) that signs quotes and facilitates settlement. It also references @x402/evm and signing/broadcast semantics. These are concrete crypto payment primitives (wallet private key signing, USDC on Base), which constitute direct financial execution capability.