The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, which represents a potential attack surface where untrusted data could influence agent behavior.
Ingestion points: External data is fetched via WebFetch from token-api.kyberswap.com and aggregator-api.kyberswap.com (Steps 1, 2, 3, and 4).
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the fetched data.
Capability inventory: The skill utilizes WebFetch for network operations and reads local files such as token-registry.md and api-reference.md.
Sanitization: The instructions mandate exact symbol matching and verification against market capitalization or whitelist status to ensure data integrity.
Context: This risk is considered standard for tools designed to aggregate real-time market data from external APIs and is mitigated by the fact that the data sources are official vendor-owned services.

token-info