The Agent Skills Directory

[SAFE]: The skill defines a structured workflow for generating advertisement materials using built-in platform tools such as generate_image, generate_video, and tts. Analysis of the instructions and workflow revealed no malicious intent, unauthorized network activity, or sensitive data access.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes untrusted user input to generate content.
Ingestion points: User-provided product details, benefits, and brand guidelines are used to form the basis of generated scripts and tool prompts.
Boundary markers: None present; the skill lacks delimiters or explicit instructions to ignore potentially malicious commands within the user-provided data.
Capability inventory: Access to media generation tools (generate_video, generate_image, generate_music, tts) as defined in SKILL.md.
Sanitization: The skill does not implement validation or sanitization of the input data before it is interpolated into tool instructions.

ad-commercial-kit