The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from collaborative canvas projects, including project titles, node labels, and prompts, which are external data sources.
Ingestion points: Data is ingested through tools such as list_projects, list_nodes, and get_node, which read live state from collaborative documents.
Capability inventory: The skill possesses capabilities to create and update nodes, generate various media types (image, video, audio, 3D, storyboard) based on prompts, and establish connections between nodes.
Boundary markers: The instructions do not specify the use of delimiters or specific warnings for the agent to ignore potentially malicious instructions embedded in the project or node data.
Sanitization: There is no mention of sanitization or validation logic for the content retrieved from the collaborative canvas environment.

flowy-canvas