The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external currency data fetched from APIs, creating a surface where malicious instructions could potentially influence agent behavior.
Ingestion points: External currency and historical rate data retrieved via sandbase_call_tool using the strale_currency_convert and strale_exchange_rate tools.
Boundary markers: There are no explicit delimiters or instructions provided in SKILL.md to isolate tool outputs from system instructions.
Capability inventory: The skill possesses network research capabilities via the sandbase_call_tool gateway.
Sanitization: No input validation or output sanitization is mentioned for the data returned from the conversion tools before it is synthesized for the user.

currency-converter