The Agent Skills Directory

[SAFE]: The skill instructions are strictly focused on financial analysis and do not contain any patterns associated with prompt injection, privilege escalation, or persistence. All referenced tools are domain-specific and used for their intended analytical purpose.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes external market data from multiple sources. While this exposes the agent to indirect prompt injection, the risk is negligible due to the lack of high-risk capabilities like shell execution or file system writes.
Ingestion points: The skill ingests data from equity_vol_surface, fx_vol_surface, tscc_historical_pricing_summaries, and qa_historical_equity_price (SKILL.md).
Boundary markers: No explicit delimiters are defined in the instructions to isolate tool outputs from the agent's core logic.
Capability inventory: Capabilities are limited to data interpretation and strategic recommendation using the provided financial tools.
Sanitization: No explicit sanitization or validation logic is provided for the incoming data streams.

option-vol-analysis