altshuller-perspective
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to process user queries alongside data retrieved from the external Zhihuiya MCP service.
- Ingestion points: User input and data outputs from the '智慧芽开放平台 MCP' tool (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters to isolate external tool output from the reasoning prompt.
- Capability inventory: The skill performs data retrieval and systematic analysis using external tool capabilities.
- Sanitization: No explicit sanitization or validation logic is defined for processing external data.
- [SAFE]: The skill references official vendor resources for its functionality. The link to 'open.zhihuiya.com' is the authorized developer portal for the skill's author (PatSnap), representing a standard and legitimate dependency for the MCP service.
Audit Metadata