The Agent Skills Directory

[SAFE]: The skill serves as a documentation resource for the @tanstack/table-core library. All code snippets are standard implementation patterns for row aggregation and do not contain malicious commands, unauthorized data access, or obfuscation.
[PROMPT_INJECTION]: The skill handles untrusted table data through its aggregation logic, which constitutes an indirect prompt injection surface.
Ingestion points: Untrusted data is processed via the rows array and the getValue accessor within aggregation functions described in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters provided to the agent to differentiate between instructions and the data contained within the table rows.
Capability inventory: The skill does not implement any high-risk capabilities such as file system writes, network operations, or shell command execution.
Sanitization: The provided examples do not include sanitization or validation of the input row data before it is processed by the aggregation functions.

tanstack-table-core-aggregation