yuque-personal-style-extract

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill behavior matches its stated purpose of analyzing writing styles within the Yuque platform. It uses specific MCP tools to interact with the user's data.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to document ingestion.
  • Ingestion points: document content is ingested via 'yuque_get_doc' as described in SKILL.md.
  • Boundary markers: the instructions do not specify delimiters to isolate external document content from the agent's internal prompt logic.
  • Capability inventory: the skill is limited to 'yuque_search', 'yuque_get_doc', and 'yuque_list_repos', which are non-destructive read operations within the Yuque environment.
  • Sanitization: the skill does not implement sanitization or filtering of the document content before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 07:21 AM