yuque-personal-reading-digest

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes untrusted content from external documents.
  • Ingestion points: Content is ingested from Yuque documents using the yuque_get_doc tool (File: SKILL.md).
  • Boundary markers: The instructions do not define clear delimiters or provide 'ignore instructions' warnings to prevent the LLM from obeying commands embedded within the fetched document content.
  • Capability inventory: The skill has the ability to search documents, list repositories, and create new documents via the yuque_search, yuque_list_repos, and yuque_create_doc tools (File: SKILL.md).
  • Sanitization: The skill does not perform any sanitization or validation of the document content before passing it to the model for summarization.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 07:21 AM