tuning-incremental-sync-config
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted metadata from external data sources which represents a potential attack surface for indirect prompt injection.
- Ingestion points: Data enters the agent's context through
external-data-schemas-retrieveandexternal-data-schemas-incremental-fields-create(SKILL.md), which fetch schema details and available columns from user-controlled databases. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when processing retrieved schema metadata.
- Capability inventory: The skill possesses potentially destructive capabilities, including
external-data-schemas-partial-update(modifying configuration),external-data-schemas-delete-data(dropping synced tables), andexternal-data-schemas-resync(wiping and re-importing data). - Sanitization: There is no evidence of validation or sanitization of external content (like column names) before it is interpolated into the workflow or tool arguments.
Audit Metadata