The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data analytics tasks which may involve untrusted data or SQL queries that could contain embedded instructions intended to influence the agent.
Ingestion points: The skill activates on user requests related to data analytics, SQL queries, statistical analysis, and business intelligence (SKILL.md).
Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the data being analyzed.
Capability inventory: The skill allows access to powerful tools including Bash, Write, Edit, Read, and Grep, providing a significant interaction surface for potential injections (SKILL.md).
Sanitization: There is no evidence of sanitization, validation, or escaping logic for external data in the provided skill instructions.

aggregation-helper