The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize information from external sources (web, news, scholar, and industry data), which exposes the agent to potential malicious instructions embedded in those sources.
Ingestion points: Data entering the agent context includes results from tavily_search, exa_search, scholar_search_mixed, google_news_bulk_articles, apollo_company_search, and akta_industry_search as defined in SKILL.md.
Boundary markers: There are no specific instructions or delimiters provided to help the agent distinguish between its core instructions and the external data it processes.
Capability inventory: The skill relies on network-based tool invocations via a gateway (sandbase_call_tool) to retrieve research data.
Sanitization: The instructions do not define any sanitization or filtering protocols for the content fetched from the research tools.

market-research