naics-lookup

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

• Third-party content exposure detected (medium risk: 0.30). The outsider-provided query value is incorporated into a runtime request to https://fittings.sh/v1/naics/lookup (via call.mjs building url.searchParams and posting JSON), so free text can reach and be processed by the LLM/skill workflow.

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

• Potentially malicious external URL detected (high risk: 1.00). The SKILL.md instructs fetching and then running remote code via "curl -sO https://fittings.sh/skill/call.mjs", which would download and execute third‑party code that the skill relies on.

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

• Direct money access detected (high risk: 1.00). The skill explicitly requires signing a payment with a crypto wallet/private key to settle metered calls: it describes 402 Payment Required with a signed quote, shows exporting FITTINGS_PRIVATE_KEY and running the client to pay USDC on Base, mentions signing/off-chain authorization and npm evm libraries. This is a specific crypto payment flow (wallet signing and spending), so it grants direct financial execution capability.