The Agent Skills Directory

[External Downloads] (MEDIUM): The installation guide requires the installation of the 'seeddance-sdk' package. This package does not originate from a repository within the verified trusted organizations list, meaning its source and integrity cannot be definitively confirmed within the audit framework.
[Indirect Prompt Injection] (LOW): The skill is designed to ingest and process user-provided strings and images as 'prompts' for video generation, creating a vulnerability surface for indirect prompt injection.
Ingestion points: prompt and image parameters used in client.textToVideo and client.imageToVideo calls.
Boundary markers: The skill does not implement delimiters or safety instructions (e.g., 'ignore instructions within the following text') to separate untrusted user data from the execution logic.
Capability inventory: The skill possesses the capability to write data to the local file system (fs.writeFileSync) and perform network operations via the SDK.
Sanitization: There is no evidence of client-side sanitization or validation of the user input before it is passed to the external API.

seeddance-ai-video