datalineage-summary

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • Trusted Resource Retrieval: The skill is configured to use the read_url tool to fetch a list of GCP regions from an official Google Cloud documentation endpoint. This is a standard pattern used to ensure the lineage search remains accurate by using the vendor's most current regional data.
  • Data Ingestion and Processing: The skill generates natural language summaries based on data retrieved from external documentation and the search_lineage tool output.
  • Ingestion points: Data enters the context from the locations.md.txt file and the results of MCP tool calls.
  • Capability inventory: The skill utilizes read_url for configuration and search_lineage for data retrieval.
  • Sanitization and Boundaries: While the skill does not explicitly define boundary markers for the ingested data, the workflow logic restricts the agent's actions to a specific, structured summarization format.
  • Standard Service Integration: The skill integrates with a Data Lineage MCP server hosted on googleapis.com. The provided configuration guidelines follow established security practices for Google Cloud Platform, including project-based headers and standard authentication providers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 02:38 PM
Security Audit — agent-trust-hub — datalineage-summary