The Agent Skills Directory

[SAFE]: The skill is a text-based template for generating video prompts. It does not perform any file system operations, network requests, or command executions.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text to populate a video prompt template (the [line] placeholder). This creates a surface for indirect prompt injection where a user might attempt to inject instructions into the generated prompt. However, because the skill has no autonomous capabilities or tool-access beyond text generation, and the input is delimited by double quotes within the template, the risk is negligible.
[METADATA_POISONING]: The skill's metadata and descriptions accurately reflect its functionality. The use of disable-model-invocation: true in the frontmatter is a defensive configuration that limits the agent's capability, enhancing security.

simple-talking-head