skills/tanstack/table/aggregation/Gen Agent Trust Hub

aggregation

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements logic to process and aggregate data from table rows, which represents an ingestion surface for untrusted content.
  • Ingestion points: Data enters the skill's context through row models passed to aggregation functions such as getAggregationValue and the aggregate callback in constructAggregationFn (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions for the agent to ignore potentially malicious instructions embedded within the table data.
  • Capability inventory: The skill's capabilities are primarily mathematical and data-transformative. It lacks high-risk capabilities such as network exfiltration, arbitrary command execution, or sensitive file system writes.
  • Sanitization: The provided examples do not demonstrate input sanitization or validation, relying on the library's internal handling of row values.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 02:17 PM
Security Audit — agent-trust-hub — aggregation