The Agent Skills Directory

[COMMAND_EXECUTION]: The skill initiates the execution of a local Python script (scripts/generate_image.py) to manage image generation and local file saving. This is a core component of the skill's storyboard creation workflow.
[EXTERNAL_DOWNLOADS]: The Python script makes network requests to generativelanguage.googleapis.com. This is an informative finding involving a well-known service from a trusted organization (Google) used as intended for the skill's primary purpose of image generation.
[PROMPT_INJECTION]: The skill architecture presents a surface for indirect prompt injection by processing untrusted user input to drive tool behavior.
Ingestion points: User-supplied story descriptions and scene names are ingested during Phase 1 and Phase 4 of the skill's workflow.
Boundary markers: The prompt construction lacks clear delimiters or protective instructions to ensure the model disregards potentially malicious commands embedded in the user's input.
Capability inventory: Through the generate_image.py script, the skill has the capability to perform network operations and write files to the local file system.
Sanitization: No evidence of sanitization or validation of user-provided content was found before its inclusion in API prompts or command arguments, which could theoretically be used to influence prompt logic or local file naming.

space-storyboard-generator