datalineage-summary

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill dynamically fetches a list of GCP locations from an official Google Cloud documentation URL (https://docs.cloud.google.com/dataplex/docs/locations.md.txt) to populate search parameters for lineage discovery.
  • [COMMAND_EXECUTION]: The instructions direct the agent to use standard Google Cloud utilities, specifically bq show and gcloud storage ls, to determine asset regions when necessary.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external Data Lineage graph metadata, creating a potential surface for indirect prompt injection if the graph nodes contain instructions.
  • Ingestion points: Lineage links and process metadata retrieved from the search_lineage MCP tool.
  • Boundary markers: The skill uses specific Markdown headers for structure but lacks explicit delimiters to isolate external data from instructions.
  • Capability inventory: The skill uses the search_lineage, read_url, bq, and gcloud tools.
  • Sanitization: No specific sanitization or filtering logic is described for the text content within the lineage nodes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:41 AM
Security Audit — agent-trust-hub — datalineage-summary