The Agent Skills Directory

[SAFE]: The skill performs standard business logic for profitability analysis. It utilizes internal tools (transaction_search, spending_summary) for their intended purposes and does not exhibit any signs of prompt injection, data exfiltration, or unauthorized code execution.
[INDIRECT_PROMPT_INJECTION]: The skill processes transaction data (revenue and expenses) which is an untrusted ingestion point. However, the capabilities are limited to data aggregation and summary calculation within the agent's context, with no dangerous side effects (like file writes or network requests) that could be triggered by malicious data content.

client-profitability