The Agent Skills Directory

[DATA_EXPOSURE]: The skill accesses the sensitive file path ~/.pixazo/api-key to retrieve and store the PIXAZO_API_KEY required for operation. It also reads the PIXAZO_API_KEY environment variable.
[EXTERNAL_DOWNLOADS]: The skill fetches reference documentation and model schemas from https://www.pixazo.ai/models/pixelcut.md to guide its internal operations.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data, such as image prompts and URLs, which creates a vulnerability surface for indirect prompt injection.
Ingestion points: User-supplied text prompts and reference image/video URLs are ingested for use in API requests.
Boundary markers: The skill lacks explicit instructions for using delimiters or boundary markers to isolate user-provided content within the API request payloads.
Capability inventory: The skill uses curl, Python requests, and Node.js fetch to perform network operations based on user input.
Sanitization: There are no documented steps for validating or sanitizing the input data before it is interpolated into network requests.
[COMMAND_EXECUTION]: The skill provides the agent with specific code snippets for curl, Python, and Node.js to execute network operations against the Pixazo API gateway.

pixelcut