The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to search and summarize external data from academic databases and the web, which introduces an attack surface for indirect prompt injection.
Ingestion points: Data enters the agent's context through the scholar_search_scholar, scholar_search_web, and scholar_search_mixed tools (referenced in SKILL.md and references/sandbase-api-map.md).
Boundary markers: The skill does not define explicit delimiters or instructions to ignore potential commands embedded in the search results.
Capability inventory: The skill utilizes sandbase_call_tool to execute searches and scholar_explain to generate AI-powered summaries of the findings.
Sanitization: There is no evidence of content sanitization or filtering to prevent the agent from obeying instructions hidden within processed research papers or web pages.

academic-research