The Agent Skills Directory

[SAFE]: No prompt injection or behavior override instructions were found. The content consists of legitimate technical documentation for a search tool.
[SAFE]: No evidence of data exfiltration or credential harvesting. The skill does not access sensitive local files or environment variables.
[SAFE]: No obfuscation or hidden content was detected. All instructions and parameters are provided in clear text.
[SAFE]: The skill does not download external scripts or execute remote code. It utilizes the vendor's own search tool (web_search_advanced_exa) for information retrieval.
[SAFE]: Although the skill processes external web data (search results), which is a common surface for indirect prompt injection, this is inherent to its primary purpose as a search tool and does not involve any unsafe downstream execution (such as eval or file writing).

web-search-advanced-financial-report