treasury-reporting-rate

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). These URLs point to a third-party site that hosts and distributes an executable JavaScript client (call.mjs) and the skill explicitly instructs users to download and run it — fetching and executing remote code from an unverified source is a security risk.

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

• Third-party content exposure detected (low risk: 0.10). The runtime path in call.mjs only ingests first-party service JSON fetched from https://fittings.sh/catalog/... and then performs a payment-wrapped fetch of a first-party fittings.sh service endpoint; it does not read outsider-authored free text from any inbox/feed/queue/user-submitted content without first selecting a specific serviceId/endpoint.

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

• Potentially malicious external URL detected (high risk: 0.90). SKILL.md explicitly instructs fetching and then running remote code with "curl -sO https://fittings.sh/skill/call.mjs" which downloads executable JS that users are expected to run (node call.mjs), so this 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 explicitly describes a paid API flow that requires signing an on‑chain/crypto authorization with a wallet private key (FITTINGS_PRIVATE_KEY), using USDC on Base, and references EVM tooling (@x402/evm). It instructs how to perform real payments (402 Payment Required, sign an authorization, facilitator settles) and shows commands to set a private key and execute a paid call. These are specific crypto/blockchain payment instructions — not generic HTTP or browser automation — so it grants direct financial execution capability.