rail
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external web pages on the official 12306.cn domain.
- Ingestion points: Web pages from 12306.cn accessed via browser tools as specified in SKILL.md.
- Boundary markers: None explicitly defined to separate untrusted web content from instructions.
- Capability inventory: Web browsing and information retrieval.
- Sanitization: No explicit filtering of the retrieved content is mentioned.
- Context: Data ingestion is restricted to a well-known official rail service for lookup purposes.
Audit Metadata