The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown files and templates. There are no scripts, binaries, or executable components provided within the skill package.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided content (blog posts, videos, newsletters), which constitutes an indirect prompt injection surface. However, the total lack of dangerous tools, network capabilities, or sensitive file access renders this surface effectively non-exploitable. 1. Ingestion points: User-provided creative content and published material specified in the exploration modes. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided templates. 3. Capability inventory: No tools or capabilities detected across all files. 4. Sanitization: No explicit sanitization of external content is described.

ebook-discovery