The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain hidden instructions designed to influence the agent's behavior.
Ingestion points: The skill accepts several external inputs including image_path, image_paths, mask_path, audio_url, video_url, and start_image_url across various media generation tools.
Boundary markers: The instructions do not specify any boundary markers or delimiters to isolate these untrusted inputs from the agent's core instructions.
Capability inventory: The skill enables capabilities such as network requests (to AI providers like Fal, Replicate, and OpenAI) and file system access (for reading local assets and persisting job checkpoints).
Sanitization: There is no evidence of sanitization, filtering, or validation of the content within the ingested media files or URLs to prevent prompt injection attacks.

provider-model-refresh