fittings-hts-search

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). Most entries are API/documentation endpoints, but https://fittings.sh/skill/call.mjs is a direct-download JavaScript module the doc instructs you to curl and execute, a high-risk pattern for distributing malware.

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow reads only the outsider-provided query string from GET https://fittings.sh/v1/hts/search to perform a tariff lookup, meaning the LLM ingests free text submitted by the user directly into the search call.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs fetching and executing remote code with "curl -sO https://fittings.sh/skill/call.mjs" and then running "node call.mjs", so https://fittings.sh/skill/call.mjs is a runtime external dependency that executes remote code.

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 API that requires signing an authorization with a wallet/private key and settling in USDC on Base. It instructs exporting FITTINGS_PRIVATE_KEY, running node call.mjs to "pay for real," and references @x402/evm (crypto signing/EVM tooling). Those are specific crypto/payment integrations that enable an agent to sign and authorize real payments, i.e., direct financial execution.