sec-filing-search

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). These URLs point to an unvetted domain that explicitly instructs users to download and run an executable script (call.mjs) via curl, which is a direct executable download from a non-official source and therefore suspicious.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow posts the user-provided q (and optional forms/limit) into the GET https://fittings.sh/v1/sec/filing-search endpoint, which performs SEC full-text search and returns results that the LLM client ingests as response text.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs the operator to download and then run remote code (curl -sO https://fittings.sh/skill/call.mjs followed by running node call.mjs), so https://fittings.sh/skill/call.mjs is a runtime external dependency that fetches executable 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 the client to sign a quoted payment authorization with a private key (FITTINGS_PRIVATE_KEY), references holding USDC on Base, and shows commands to export a wallet key and perform the signed call. This is an explicit crypto-wallet signing/payment flow (off-chain authorization, facilitator settlement), i.e., direct financial execution capability.