The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data retrieved from external web sources. * Ingestion points: Data from external search tools like tavily_search and exa_search is ingested into the agent context during the research process. * Boundary markers: The instructions do not specify the use of delimiters or specific commands to isolate the external content from the agent's core instructions. * Capability inventory: The skill has the capability to perform multiple external searches and synthesize that information into a final response. * Sanitization: There are no explicit instructions to sanitize or validate the content returned from external APIs before it is interpolated into the agent's reasoning process.

market-research