datacommons-client

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • Unverifiable Dependencies & Remote Code Execution (SAFE): The skill installs the datacommons-client package via uv pip. This is a verifiable and standard dependency for accessing the Data Commons service.\n- Indirect Prompt Injection (LOW): The skill ingests untrusted data from the external Data Commons API, which could theoretically contain instructions intended to influence the agent's behavior.\n
  • Ingestion points: Statistical and metadata results from client.observation.fetch, client.node.fetch, and client.resolve.fetch.\n
  • Boundary markers: Absent in the code snippets provided in the documentation.\n
  • Capability inventory: Performs network requests to datacommons.org and processes retrieved data using the Pandas library.\n
  • Sanitization: No explicit sanitization or escaping of the fetched API data is shown in the usage examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:23 PM