dingtalk-ai-table
Warn
Audited by Snyk on Apr 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill explicitly calls an external DingTalk MCP Server (the Streamable HTTP URL obtained from https://mcp.dingtalk.com) via mcporter (see SKILL.md's required "mcporter list dingtalk-ai-table --schema" check and repeated use of "mcporter call ... get_fields / query_records / create_records" in the recommended workflow and scripts) and parses the returned JSON schema/fields/records/attachment URLs as part of normal operation, so it ingests untrusted, potentially user-generated third‑party content that can materially change tool use or decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata