The Agent Skills Directory

[SAFE]: The skill is entirely composed of Markdown instructions and reference documents. It does not contain any executable scripts, shell commands, or external package dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze user-provided story texts. While this represents an entry point for untrusted data, the skill has no dangerous capabilities (such as file system writes, network requests, or code execution) that could be exploited through malicious content in the story text. The risk is considered minimal and inherent to the intended use case.
[FRONTMATTER]: The YAML frontmatter clearly defines the skill's scope and explicitly states it should not be used when network connectivity or external data retrieval is required, aligning with safe operational boundaries.

novel-evaluator