antv-g6-graph

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the curl tool to interact with a documentation retrieval API at sive.antv.antgroup.com. This service is used to provide the agent with relevant API context, examples, and configuration guidelines for G6 v5.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from the AntV documentation service to inform its responses. While this creates a theoretical surface for indirect instructions, the source is a vendor-managed project resource intended for information retrieval.
  • Ingestion points: API responses from sive.antv.antgroup.com described in the Content Retrieval Service section.
  • Boundary markers: None specified in the instructions for the retrieved data.
  • Capability inventory: curl tool for network retrieval; generation of JavaScript code for graph visualization.
  • Sanitization: No specific sanitization or validation steps are defined for the fetched markdown documentation content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:40 AM
Security Audit — agent-trust-hub — antv-g6-graph