yuque-group-weekly-report
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for Indirect Prompt Injection. \n- Ingestion points: Data is ingested from the Yuque API via tools yuque_group_doc_stats, yuque_group_member_stats, and yuque_list_repos (defined in SKILL.md). This data includes potentially attacker-controlled strings like document titles and member names. \n- Boundary markers: There are no explicit delimiters or instructions to the model to ignore potential commands embedded within the fetched document metadata during analysis or report generation. \n- Capability inventory: The skill possesses the yuque_create_doc capability (defined in SKILL.md), which allows it to write content back to the Yuque platform. \n- Sanitization: No sanitization or validation logic is present to filter out malicious instructions from the fetched data before it is interpolated into the final report body.
Audit Metadata