The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network operations to the vendor's API endpoint to process prompts.
Evidence: The skill makes HTTP POST requests to https://api.scavio.dev/api/v1/gemini/prompt using the requests library.
Context: These operations are directed to the official API of the skill's vendor (scavio-ai) and are required for the skill's primary functionality.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content returned from the external Google Gemini LLM via the Scavio API.
Ingestion points: The agent is instructed to read data from answer.markdown, sources, and shopping fields returned by the remote API.
Boundary markers: Documentation advises the agent to quote the Markdown output and surface source URLs for verification, which helps distinguish external data from the agent's internal reasoning.
Capability inventory: The skill performs network requests using the requests library; while not directly executing code, the retrieved content is processed by the agent.
Sanitization: There are no explicit instructions for sanitizing or escaping the Markdown content returned from the external model before it is processed by the agent.

gemini-scraper-api