The Agent Skills Directory

[SAFE]: The skill serves as an instructional guide for using media generation tools. It incorporates safety guidelines regarding the creation of synthetic testimonials and follows standard platform procedures for tool discovery and file management. No malicious patterns, obfuscation, or unauthorized access attempts were detected.- [INDIRECT_PROMPT_INJECTION]: The skill handles user-provided scripts and dialogue as input. This is a standard attack surface for indirect prompt injection where malicious instructions could be embedded in the dialogue.
Ingestion points: User-provided scripts in the prompt field and style_instructions within the SKILL.md instructions.
Boundary markers: No explicit delimiters or boundary markers are defined for the prompt input.
Capability inventory: The skill uses list_base_models, get_base_model, and request_file_upload_url to interact with external models and services.
Sanitization: No technical sanitization is mentioned, though the instructions mandate an ethical review of the script content by the agent before generation.

layer-talking-characters