fittings-fema-disaster-declarations

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly shows exporting FITTINGS_PRIVATE_KEY in plaintext and states the key "sits in plaintext wherever the agent runs," which encourages embedding a private key in environment/commands and could lead the LLM to handle or output the secret verbatim.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). One URL is a direct download of an executable script (call.mjs) from an unverified domain and the document explicitly instructs downloading and running it, which is a high-risk pattern for malware distribution.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs downloading and executing remote code with "curl -sO https://fittings.sh/skill/call.mjs" followed by "node call.mjs", meaning external content at https://fittings.sh/skill/call.mjs would be fetched and executed at runtime.

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

• Direct money access detected (high risk: 1.00). The skill embeds a metered payment flow that requires signing an authorization with a private key (FITTINGS_PRIVATE_KEY) and using USDC on Base to settle calls. It explicitly instructs setting a wallet private key, describes signing the quote/authorization, and caps auto-spend — i.e., it exposes a crypto payment signing/execution capability rather than being purely informational. Those explicit wallet/payment instructions constitute direct financial execution capability.