The Agent Skills Directory

Indirect Prompt Injection Surface: This skill is designed to ingest and process information from various external and internal sources, such as company documents, team communications, and public market benchmarks. This capability introduces a potential surface for indirect prompt injection, where instructions embedded within the processed data could attempt to influence the agent's behavior.
Ingestion points: Data is retrieved from context lanes including ~~company_docs and ~~team_communication (referenced in SKILL.md), as well as public sources for market data.
Boundary markers: The instructions do not specify the use of strict boundary markers, such as XML tags or specific delimiters, to isolate untrusted data during processing.
Capability inventory: The skill utilizes tools like $jupyter-notebooks for analytical calculations and $spreadsheets for data presentation, which are invoked during the modeling phase.
Sanitization: No explicit sanitization or filtering logic is defined for the content retrieved from external sources before it is processed by the agent.

market-sizing