antv-x6-editor
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches documentation and technical context from the vendor's official API server at
https://sive.antv.antgroup.com. - [INDIRECT_PROMPT_INJECTION]: The skill incorporates external content into the agent's context at runtime. This creates a theoretical surface for indirect prompt injection, though the risk is mitigated by using a trusted vendor source. Evidence Chain: (1) Ingestion points:
https://sive.antv.antgroup.com/api/v1/context/retrieve(2) Boundary markers: Absent (3) Capability inventory: Network access viacurl(4) Sanitization: Absent.
Audit Metadata