The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data by scraping content from report URLs using the tools context_dev_scrape_markdown and context_dev_extract_structured_data. This creates a vulnerability surface where instructions hidden within the external reports could potentially manipulate the agent's output or logic.
Ingestion points: Data is ingested via tool calls defined in references/sandbase-api-map.md to extract structured data or markdown from report pages.
Boundary markers: The instructions do not specify the use of delimiters or provide explicit directives to the agent to disregard instructions found within the processed reports.
Capability inventory: The skill utilizes sandbase_call_tool to perform data extraction and analysis tasks.
Sanitization: There are no instructions for sanitizing or validating the content retrieved from the external URLs before it is processed by the agent.

variance-analysis