weekly-report
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes data from the Yuque API (titles, names, activities) and interpolates it into a report template, which could be exploited if an attacker controls those fields.
- Ingestion points: Activity data fetched via
yuque_group_doc_stats,yuque_group_member_stats, andyuque_list_reposinSKILL.md. - Boundary markers: Absent; data is directly placed into markdown tables within the report body.
- Capability inventory: The
yuque_create_doctool allows writing data back to the Yuque platform. - Sanitization: No validation or escaping is described for the content retrieved from external API calls.
Audit Metadata