fittings-regulations-document-search

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). These URLs include a direct link to an unverified .mjs script (https://fittings.sh/skill/call.mjs) that the skill explicitly asks you to download and execute with node, which is a high-risk pattern for distributing malicious code.

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow ingests outsider-authored free text via the user-supplied query parameter in the runtime call GET https://fittings.sh/v1/regulations/document-search, which performs full-text search over Regulations.gov documents.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill includes shell commands that download and execute remote JavaScript (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 can execute 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 request flow that requires signing an authorization with an on-chain wallet private key (FITTINGS_PRIVATE_KEY), uses USDC on Base, and references EVM tooling (@x402/evm). It instructs setting a private key and running a client that will sign payment authorizations so a facilitator can settle gas—i.e., it enables crypto wallet-based payments. This is a specific crypto/blockchain payment capability, which constitutes direct financial execution authority.