The Agent Skills Directory

[SAFE]: The skill instructions define a benign workflow for financial analysis. No malicious patterns, such as prompt injection, data exfiltration, or unauthorized command execution, were found in the skill body or metadata.
[DATA_EXPOSURE]: While the skill processes sensitive financial transaction data, it does so using specific tools (spending_summary, transaction_search) intended for this purpose. The analysis occurs within the local context and does not involve network operations or exfiltration to external domains.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external data (bank transactions) which is a theoretical injection surface; however, the skill's capabilities are limited to data summarization and presentation. No high-risk capabilities like arbitrary command execution or network writing are present that could be exploited via malicious transaction descriptions.

spending-review