bulk-operations
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements functions to ingest and process external datasets and files, creating a surface for indirect prompt injection.
- Ingestion points: Functions like
stream_large_file,bulk_insert_records,bulk_update, andbulk_upsertinSKILL.mdtake external file paths or data structures as input. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present when processing this data.
- Capability inventory: The skill possesses significant capabilities including database write/update operations (
commit,update), file system read access (open), and parallel execution (ProcessPoolExecutor). - Sanitization: There is no evidence of data sanitization or validation performed on the records or file content before processing.
Audit Metadata