The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the genmedia CLI for model discovery, schema inspection, and executing media generation jobs, which is necessary for its core functionality.
[EXTERNAL_DOWNLOADS]: Generated media is downloaded from established service providers (e.g., fal.ai, OpenAI, Veed) using the genmedia status command as part of the intended workflow.
[DATA_EXFILTRATION]: User-provided media files (images, audio, video) are uploaded to selected service endpoints to facilitate video production, which is the primary purpose of the skill.
[PROMPT_INJECTION]: The skill ingests user-supplied scripts and descriptions, serving as an attack surface for indirect prompt injection.
Ingestion points: User-provided product details, scripts, and media are used as inputs for building prompts in the genmedia tool (SKILL.md).
Boundary markers: No explicit delimiters or boundary markers are used to isolate user-provided text from the agent's instructions during prompt construction.
Capability inventory: The skill can upload local files, trigger remote generation jobs, and write downloaded files to the local disk (SKILL.md).
Sanitization: No explicit sanitization or validation of user-provided script content is specified beyond general instructions to the agent to avoid fake claims.

ugc