The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and templates designed to guide an AI agent through the process of scoping, searching, and synthesizing scholarly research.
[NO_CODE]: There are no scripts, shell commands, or dynamic execution patterns present in the provided files.
[DATA_EXPOSURE]: The skill does not access sensitive local file paths or environment variables. It focuses on external scholarly databases which are accessed via standard agent capabilities if available.
[PROMPT_INJECTION]: The instructions are clear, academic, and do not contain patterns intended to bypass safety filters or override system instructions.
[INDIRECT_PROMPT_INJECTION]: While the skill is intended to process external scholarly data, it does not possess any dangerous capabilities (such as file-writing or network exfiltration tools) that could be exploited by malicious content within those sources.

sota-survey