The Agent Skills Directory

[PROMPT_INJECTION]: The skill documents a workflow where user-provided strings are interpolated into complex prompt templates and passed to video generation tools, creating a surface for indirect prompt injection.
Ingestion points: The prompt parameter used in the video_selector.execute and seedance_video.execute code examples in SKILL.md.
Boundary markers: The skill lacks specific delimiters or instructions to ignore malicious commands embedded within the user-provided prompt content.
Capability inventory: The skill is configured with Bash, Read, and Write tools and makes network calls to external AI providers (fal.ai, Replicate, Runway, etc.).
Sanitization: There is no evidence of input validation or escaping for the prompt data before it is sent to the model endpoints.

seedance-2-0