The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external crypto markets and token discovery tools which could contain untrusted instructions.
Ingestion points: Data enters the agent context through tools like search_tokens, discover_tokens, get_market_overview, and get_price which fetch token metadata and market state from external venues.
Boundary markers: The instructions do not specify the use of boundary markers or delimiters to isolate untrusted market data from the agent's core logic.
Capability inventory: The skill includes high-impact capabilities such as submit_decision for executing trades and adjust_risk_limits for changing operational constraints.
Sanitization: No explicit content validation or sanitization procedures are defined for the data retrieved from external trading environments.

crypto-trading