dingtalk-openapi-skill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a curated OpenAPI schema from the vendor's official GitHub repository (holon-run/uxc) to define the DingTalk messaging operations for the uxc tool.
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external DingTalk API data, creating a potential ingestion surface. Ingestion points: User detail responses from the /contact/users/{unionId} endpoint. Boundary markers: No specific delimiters or safety instructions are defined for processing the ingested user data. Capability inventory: High-risk messaging operations including batch sends to users and group message delivery. Sanitization: The skill relies on the uxc tool to handle data as structured JSON, which provides inherent structure but not specific content sanitization for the IM messages themselves.
Audit Metadata