tuning-incremental-sync-config
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes metadata from external, potentially user-controlled databases, which serves as an injection surface.
- Ingestion points: Metadata including table names, column names, and supported sync types are retrieved via the
external-data-schemas-retrieveandexternal-data-schemas-incremental-fields-createtools. - Boundary markers: The instructions do not define explicit delimiters or security warnings to treat the retrieved external metadata as untrusted content.
- Capability inventory: The skill possesses significant capabilities for modifying and deleting data synchronization schemas via
external-data-schemas-partial-update,external-data-schemas-resync, andexternal-data-schemas-delete-data. - Sanitization: There is no evidence of sanitization or validation logic applied to the external metadata before it is passed to other tools or used in decision-making logic.
Audit Metadata