The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user content (via file paths or pasted text) which is then analyzed to generate storyboards and image prompts.
Ingestion points: Source content provided by the user is saved to source.md or read directly as input for analysis.
Boundary markers: The prompt templates for analysis and storyboard generation do not include explicit delimiters or instructions to ignore embedded commands within the user's source content.
Capability inventory: The skill can execute shell commands via bun and npx, and it performs file system operations including reading, writing, and renaming files within the project and user home directories.
Sanitization: There is no evidence of sanitization or filtering of the user-provided input before it is used to generate the storyboard and image prompts.
[COMMAND_EXECUTION]: The skill executes local TypeScript scripts and shell-based environment checks during the generation process.
Evidence: The workflow calls npx -y bun ${SKILL_DIR}/../baoyu-image-gen/scripts/main.ts for image generation and npx -y bun ${SKILL_DIR}/scripts/merge-to-pdf.ts for merging images into a PDF. It also uses shell commands like test -f and test -d in workflow.md to verify the existence of configuration files and output directories.

baoyu-comic