hts-search

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). The skill instructs users to download and run an executable script (call.mjs) directly from an external domain (https://fittings.sh), which is an unverified source for executable code and therefore a potential vector for malware.

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

• Third-party content exposure detected (low risk: 0.10). The runtime workflow exposes only an explicitly provided query string (e.g., from node call.mjs hts.search query=...) to the backend GET https://fittings.sh/v1/hts/search, and it does not ingest any outsider-authored free text unless the caller supplies that parameter.

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

• Direct money access detected (high risk: 1.00). The skill explicitly supports paid calls that require signing a quote with a private key and using a crypto wallet (USDC on Base). The doc describes a 402 "Payment Required" flow, setting FITTINGS_PRIVATE_KEY, performing a real call that spends funds, and warns about using a throwaway wallet. Those are specific crypto-payment/authorization actions — i.e., the skill can be used to authorize real monetary transfers — so it grants direct financial execution capability.