fittings-lei-search

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests outsider-authored free text via the user-provided name argument that is sent as the name query parameter/body to GET https://fittings.sh/v1/lei/search for lei.search resolution.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs fetching and then running remote executable code via "curl -sO https://fittings.sh/skill/call.mjs", which downloads JavaScript that would be executed (high-confidence remote-code fetch-and-run).

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 request flow that requires an on-chain wallet/private key and signing to authorize settlement: it mentions USDC on Base, exporting FITTINGS_PRIVATE_KEY, running call.mjs to actually pay, off-chain signing by the payer and a facilitator broadcasting the transaction, and references @x402/evm and signing logic. These are specific crypto payment instructions (wallet/private-key signing and settlement), i.e. direct financial execution capability.