Stripe payments via uni CLI. Use when user wants to check balance, create payment links, manage customers, invoices, refunds, or subscriptions. Requires STRIPE_SECRET_KEY or run 'uni stripe auth'.
93
93%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Security
2 findings — 1 high severity, 1 medium severity. You should review these findings carefully before considering using this skill.
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Insecure credential handling detected (high risk: 0.80). The prompt includes examples that set the Stripe secret key directly on the command line (uni stripe auth sk_test_xxx) and as an exported value, which encourages workflows where an LLM might be asked to insert a user-provided secret verbatim into generated commands or code.
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Direct money access detected (high risk: 1.00). The skill is explicitly a Stripe payments CLI. Its documented commands perform payment actions: creating payment links (uni stripe link 50), creating and sending invoices (uni stripe invoices create ...; uni stripe invoices send in_xxx), issuing refunds (uni stripe refunds pi_xxx; uni stripe refunds pi_xxx -a 25), managing customers/subscriptions and checking balances. It requires a Stripe secret key (STRIPE_SECRET_KEY) and therefore can initiate and modify real financial transactions. This is a specific payment-gateway integration, not a generic tool, so it grants direct financial execution authority.
f1dfc90
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.