skills/legout/data-agent-skills/data-engineering-storage-remote-access-integrations-iceberg/Gen Agent Trust Hub
data-engineering-storage-remote-access-integrations-iceberg
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill suggests installing the 'pyiceberg' library along with 'pyarrow', 'pandas', and 'aws' extras. These are well-known, official packages from the Apache Software Foundation and established technology vendors.- [PROMPT_INJECTION]: The skill documents an indirect prompt injection surface related to data processing operations.
- Ingestion points: External data is ingested into the agent context via 'catalog.load_table()' and 'table.scan()' operations described in SKILL.md.
- Boundary markers: The provided examples do not include delimiters or specific instructions to the agent to ignore potentially malicious content embedded within the Iceberg tables.
- Capability inventory: The skill facilitates network operations to cloud storage providers (S3, GCS, Azure) and metadata catalogs, and it supports data modification via 'table.append()' and 'table.overwrite()' methods.
- Sanitization: No data sanitization or schema enforcement logic is included in the provided snippets to filter content retrieved from the tables.
Audit Metadata