The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes a local Python script located at scripts/search.py to perform keyword extraction and coordinate search operations. This execution is confined to the skill's own directory.
[EXTERNAL_DOWNLOADS]: The skill fetches search data from the Tavily API (api.tavily.com). This is a well-known service used for its intended purpose of providing real-time web search results.
[PROMPT_INJECTION]: The skill processes untrusted external content from search results, creating a surface for indirect prompt injection.
Ingestion points: External data is fetched by the search.py script from various web sources via the Tavily API.
Boundary markers: The skill uses Markdown headers and specific tags like <Search_Context> and <User_Question> to separate search results from the agent's instructions.
Capability inventory: The skill has the ability to execute its included Python script to retrieve data.
Sanitization: There is no explicit sanitization of the search content mentioned in the instructions or implemented in the script before it is included in the prompt context.

max-search