The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external analyst consensus and company fundamental data, which presents a surface for indirect prompt injection if the retrieved content contains malicious instructions.
Ingestion points: Data enters the agent context through the qa_ibes_consensus, qa_company_fundamentals, qa_historical_equity_price, tscc_historical_pricing_summaries, and qa_macroeconomic tools.
Boundary markers: There are no delimiters or markers used to wrap external content or instruct the agent to ignore instructions within the data.
Capability inventory: The agent's capabilities are limited to synthesising information into research snapshots; no dangerous tools such as shell execution or file system writing are used.
Sanitization: No filtering or sanitization of the external tool outputs is requested in the instructions.
[NO_CODE]: The skill consists entirely of markdown instructions and does not include any executable scripts or binary files.

equity-research