The Agent Skills Directory

[DATA_EXFILTRATION]: The skill accesses a specific sensitive file path to manage its own service credentials.
The agent is instructed to read and write the API key from ~/.pixazo/api-key and transmit it as an authentication header to the gateway.pixazo.ai endpoint.
[EXTERNAL_DOWNLOADS]: The skill fetches external configuration and documentation from the vendor's official website.
The agent is directed to fetch https://www.pixazo.ai/models/genflare.md to retrieve exact parameters and polling schemas.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes user-provided prompts and URLs to generate video content.
Ingestion points: The prompt and img_url variables within the API request bodies in SKILL.md.
Boundary markers: Absent; user input is interpolated directly into JSON payloads.
Capability inventory: Network POST requests to gateway.pixazo.ai and filesystem write access to ~/.pixazo/api-key.
Sanitization: Absent.

genflare