The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied content (e.g., article.md) to generate analysis, storyboards, and image prompts. This ingestion point represents an attack surface where malicious instructions embedded in the input data could attempt to influence the agent's behavior or poison the generated image prompts.
[COMMAND_EXECUTION]: The skill utilizes Bash and file system tools (Read, Write, Edit, Glob, Grep) to create directory structures, manage project files, and execute scripts for tasks such as PDF merging. This is within the scope of its stated functionality but represents a capability that must be monitored for safe use.
[DYNAMIC_EXECUTION]: The skill instructions include a Python snippet that modifies the runtime system path (sys.path.append('lib/shared-lib')) to load local modules. This dynamic module loading is used to interface with a 'comic_engine' located within the skill's subdirectory.

comic-generator