disclosure-completion-assistant
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted technical descriptions through input fields in the assets/disclosure-guide.html file. Although this provides an attack surface for indirect prompt injection, the skill lacks dangerous capabilities such as file writing, network operations, or command execution that could be exploited by such an injection. Evidence: 1. Ingestion points: technical description fields in assets/disclosure-guide.html; 2. Boundary markers: absent; 3. Capability inventory: none; 4. Sanitization: local JavaScript value extraction and rendering via textContent or template literals.
- [EXTERNAL_DOWNLOADS]: The documentation refers to the vendor's official MCP services and developer portals at open.zhihuiya.com and open.patsnap.com. These are legitimate resources owned by the author (Patsnap) and are used for patent data retrieval and authentication as part of the skill's core functionality.
Audit Metadata