The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes the rg (ripgrep) and file utilities to validate image paths and check file dimensions. It also executes bunx turbo typecheck to perform project-wide validation after modifying source files. These commands are typical for development environments and are limited to the project's local directory.
[PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection because it ingests data from local blog post files to generate image prompts and then modifies those same files.
Ingestion points: Reads content from TypeScript blog post definitions located in apps/landing/src/landing/blog/posts/*.ts.
Boundary markers: None are present; there are no instructions to the agent to disregard instructions that might be contained within the processed blog posts.
Capability inventory: The skill has the ability to execute shell commands (rg, file, bunx) and perform file system operations (copying images and updating source code).
Sanitization: No specific sanitization or filtering is applied to the content extracted from the blog posts before it is used in the image generation workflow.

onequery-blog-images