dingtalk-wiki
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from DingTalk knowledge bases and activity feeds while maintaining significant write capabilities, which creates a potential surface for indirect prompt injection.
- Ingestion points: External data is ingested into the agent context through search and list commands such as
+node-search,+node-list, and+feed-listas defined inSKILL.mdandreferences/wiki-node-ops.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the fetched Wiki content.
- Capability inventory: The skill possesses powerful capabilities including node creation (
+node-create), deletion (+node-delete), and member management (+member-add,+member-remove) as detailed inreferences/wiki-node-ops.mdandreferences/wiki-members.md. - Sanitization: There are no explicit instructions for the agent to sanitize or filter external content before it is processed or used in subsequent tool calls.
Audit Metadata