cn-web-search
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates fetching information from a wide variety of well-known search engines and technical platforms including Baidu, Bing, Wikipedia, GitHub, and Stack Overflow. These are recognized, well-known technology services and the usage is consistent with the skill's stated purpose of web search.
- [PROMPT_INJECTION]: As the skill's primary function is to retrieve data from the public internet, it possesses an inherent risk for indirect prompt injection, where instructions hidden in external web content could attempt to influence the agent's behavior.
- Ingestion points: Results fetched via web_fetch from search engines (SKILL.md).
- Boundary markers: No explicit boundary markers or delimiters are defined in the instructions.
- Capability inventory: The skill is instructional and does not request or implement capabilities for file-system modifications, arbitrary command execution, or sensitive data access.
- Sanitization: No sanitization or filtering logic is present for the fetched content.
Audit Metadata