tanstack-table
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests guidance data from the
/tanstack-intentcommand to influence building and migration tasks, creating a surface for indirect instructions. - Ingestion points: Guidance and intent IDs are loaded from the output of the
/tanstack-intenttool as described in SKILL.md. - Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential injection attempts within the loaded guidance data.
- Capability inventory: The skill triggers code generation, migrations, typechecking, and linting activities (SKILL.md).
- Sanitization: No validation or sanitization mechanisms are defined for the data retrieved from the intent tool.
Audit Metadata