fittings-gov-federal-spending

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). The set includes a direct download of an executable JavaScript module (https://fittings.sh/skill/call.mjs) hosted on a third‑party site, which is high risk because running such a script with Node executes unverified code; the other URLs are API/catalog endpoints and are lower risk.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a runtime workflow that POSTs user-provided JSON (recipient, limit) to https://fittings.sh/v1/gov/federal-spending, and that endpoint is the source of retrieved free-text-like data used by the agent (recipient name input is outsider-authored and used as a query).

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs fetching and running remote code via "curl -sO https://fittings.sh/skill/call.mjs" followed by "node call.mjs", meaning the fetched file (https://fittings.sh/skill/call.mjs) would be executed at runtime and thus directly controls execution.

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

• Direct money access detected (high risk: 1.00). The skill includes an explicit payment flow that requires signing authorizations with a crypto wallet: it instructs setting FITTINGS_PRIVATE_KEY, running a client that signs a quote and settles using USDC on Base, and references EVM signing libraries (@x402/evm). Those are specific crypto/payment instructions that enable spending funds (wallet signing), so this is Direct Financial Execution capability.