The Agent Skills Directory

[NO_CODE]: The skill contains no executable scripts, binaries, or source code. It consists entirely of a markdown documentation file with YAML metadata.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external websites via the web_search and web_fetch tools. * Ingestion points: External web content retrieved through web_fetch and web_search results. * Boundary markers: No specific delimiters or warnings to ignore embedded instructions are defined in the skill's markdown body. * Capability inventory: The skill facilitates network operations via search and fetch tools (such as Tavily and Jina.ai) but does not include file-write, subprocess, or dynamic execution capabilities. * Sanitization: No sanitization or filtering of the retrieved web content is specified in the skill's instructions.

meta-searching