fittings-crossref-search

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). Suspicious: the skill explicitly instructs downloading and executing an untrusted .mjs script (https://fittings.sh/skill/call.mjs), which is a direct executable payload from a third-party domain and therefore a high-risk download source.

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow is a metered bibliographic lookup that reads only the user-supplied query parameter you pass into GET https://fittings.sh/v1/crossref/search (it does not ingest arbitrary outsider-authored text sources like feeds, tickets, issues, or pages without explicit selection).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs fetching and executing remote code (curl -sO https://fittings.sh/skill/call.mjs followed by 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 documents a paid API flow that requires a crypto wallet/private key to sign an authorization and settle payment (mentions a wallet holding USDC on Base, exporting FITTINGS_PRIVATE_KEY, signing an authorization, and a facilitator settling the transaction). This is an explicit crypto/payment integration (wallet signing) that enables spending funds to call the service, so it grants direct financial execution capability.