group-knowledge-report
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection surface detected.
- Ingestion points: Untrusted data enters the context through document activity statistics (titles, popular documents) via the
yuque_group_doc_statstool inSKILL.md. - Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when interpolating external data into the report template.
- Capability inventory: The skill has the capability to write content back to the platform using the
yuque_create_doctool as described inSKILL.md. - Sanitization: There is no mention of sanitization, escaping, or validation of the ingested document metadata before it is formatted into the final report.
Audit Metadata