The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the standard requests library (version 2.31.0 or higher) via pip to facilitate communication with the Giggle API.
[COMMAND_EXECUTION]: The skill executes a Python script (scripts/trustee_api.py) to manage video generation workflows. This execution is limited to the skill's own internal logic for API interaction.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data through the diy_story parameter, which accepts user-generated scripts for video creation.
Ingestion points: The diy_story and character_info arguments in the execute_workflow function (found in SKILL.md and scripts/trustee_api.py).
Boundary markers: Data is transmitted as a JSON-encoded string within an HTTP POST request body; no specific prompt delimiters are used within the skill logic.
Capability inventory: The skill is capable of performing network operations (POST/GET) to giggle.pro. It does not have capabilities for local file system writes, system configuration changes, or arbitrary shell execution of the ingested data.
Sanitization: No client-side sanitization is performed on the story content; it is passed directly to the vendor's video generation engine.
[SAFE]: All network activity is directed to the vendor's official domain (giggle.pro) and asset storage (assets.giggle.pro). The skill correctly instructs users to manage sensitive credentials using environment variables (GIGGLE_API_KEY), which is a security best practice.

giggle-generation-drama