The Agent Skills Directory

[DYNAMIC_EXECUTION]: The exports.py file utilizes importlib.util and exec_module to dynamically load tool implementations from the internal tools/ directory. This pattern is used for modularity and to expose specific functions (get_token_security, get_token_overview, get_wallet_networth) to the agent environment.
[EXTERNAL_DOWNLOADS]: The skill performs HTTP GET requests to public-api.birdeye.so to retrieve financial data. This is the intended primary function of the skill and targets a well-known service provider in the cryptocurrency ecosystem.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: Data enters the agent's context from the Birdeye API responses via the get_token_security, get_token_overview, and get_wallet_networth functions.
Boundary markers: None explicitly used to wrap API responses.
Capability inventory: The skill possesses network communication capabilities via the requests library and proxied_get utility.
Sanitization: Responses are returned as structured JSON for the agent to interpret, which is standard for data-retrieval skills.

birdeye