group-knowledge-report
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (such as document titles, knowledge base names, and member activity) retrieved from the Yuque API. This creates a surface for indirect prompt injection where malicious content embedded in the team's data could potentially influence the agent's analysis or report generation.
- Ingestion points: Data retrieved via
yuque_group_stats,yuque_group_member_stats,yuque_group_book_stats, andyuque_group_doc_stats(SKILL.md). - Boundary markers: The skill does not define explicit delimiters or warnings to ignore instructions embedded in the retrieved data.
- Capability inventory: The skill has the capability to write data back to the platform using the
yuque_create_doctool. - Sanitization: There is no evidence of sanitization or filtering of the retrieved data before it is included in the report generation prompt.
Audit Metadata