The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various command-line tools to automate its workflow: the vendor-provided anycap CLI (for status, media generation, and vision analysis), sips (for image format optimization), and eslint (for code validation). These actions are consistent with the skill's purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process untrusted external data to generate blog posts, creating a vulnerability surface. 1. Ingestion points: Spreadsheets, JSON, bullet notes, and research provided by the user (SKILL.md). 2. Boundary markers: The skill does not define specific markers or delimiters to separate untrusted content from system instructions. 3. Capability inventory: The skill possesses capabilities for file system writes, media generation via CLI, and vision-based analysis of artifacts. 4. Sanitization: There are no documented steps for sanitizing or filtering external inputs before they are incorporated into generated content.

anycap-blog-production