iceberg
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process data from technical metadata tables, creating a potential surface for indirect prompt injection via malformed metadata.
- Ingestion points: Technical metadata tables including
snapshots,manifests,files, andpartitions(SKILL.md). - Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the ingested metadata.
- Capability inventory: The agent is guided to perform administrative and potentially destructive operations such as
expire_snapshots,remove_orphan_files, andDROP TABLE(SKILL.md). - Sanitization: No technical sanitization of metadata content is mentioned, although the skill implements human-in-the-loop safeguards by requiring explicit user confirmation before executing production-impacting maintenance tasks.
Audit Metadata