gzh-search
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The script performs network requests to
doubaoya.comto fetch article data. This is the primary function of the skill and targets the vendor's own infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill processes article titles and author names from external WeChat article sources to generate insights. This represents a potential attack surface where untrusted content could attempt to influence agent behavior, though the risk is inherent to the search functionality.
- Ingestion points: API response data (title, accountName) processed in
SKILL.md(Step 3). - Boundary markers: Data is structured into a Markdown table for presentation.
- Capability inventory: Markdown formatting and content summarization.
- Sanitization: No explicit sanitization or filtering of the article text is defined in the instruction set.
Audit Metadata