yuque-personal-stale-detector
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses established MCP tools (
yuque_list_repos,yuque_get_repo_toc,yuque_get_doc) to perform its stated purpose of document analysis. It does not attempt to exfiltrate data, bypass safety filters, or execute arbitrary code. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from document bodies to check for staleness signals. While this represents a potential injection surface, the risk is minimized because:
- Ingestion points: Document content is read via
yuque_get_doc(SKILL.md, Step 4). - Boundary markers: None explicitly defined for document parsing.
- Capability inventory: The skill is limited to reading metadata and content; it has no capabilities for file writing, network exfiltration, or command execution.
- Sanitization: Not applicable as the output is a descriptive report for the user, not a command to be executed by the system.
Audit Metadata