The Agent Skills Directory

[NO_CODE]: The skill consists entirely of natural language instructions and does not include any executable scripts, system commands, or third-party dependencies.
[SAFE]: No security issues were detected. The skill does not access the file system, make network requests, or attempt to override agent safety protocols.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided goals, which represents a data ingestion surface. However, the skill lacks any capabilities (such as shell execution or network access) that could be leveraged for an attack, and the frontmatter explicitly disables tool/model invocation.

in-your-own-words