url-expand

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly instructs setting a private key via an environment variable and shows an export FITTINGS_PRIVATE_KEY=0x... usage (and notes the key “sits in plaintext wherever the agent runs”), which encourages embedding a secret value verbatim in shell commands or agent-run contexts and thus creates an exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). The bit.ly shortened link is high-risk because URL shorteners obscure the final destination (a common malware delivery technique); the fittings.sh URLs are the documented service endpoints and appear legitimate in this skill context.

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

• Third-party content exposure detected (medium risk: 0.30). In the url.expand workflow, the skill’s endpoint GET https://fittings.sh/v1/url/expand reads the caller-supplied url at runtime and then dereferences that URL as part of the redirect-chain expansion, exposing the agent to outsider-provided destination page text.

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 call workflow that requires signing authorization with a private key (FITTINGS_PRIVATE_KEY), references holding USDC on Base, and mentions EVM-related libraries (@x402/evm). It instructs clients to sign quotes and has the client facilitate on‑chain payment via a wallet — i.e., it provides explicit crypto-wallet signing/payment functionality, which is direct financial execution capability.