qinyan-paper-search
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs network requests to
https://api.qinyanai.comto fetch literature data. This activity is expected for the skill's functionality and targets the official service endpoint. - [INDIRECT_PROMPT_INJECTION]: The skill processes and displays external content (academic paper abstracts, titles, and metadata) which constitutes a vulnerability surface.
- Ingestion points: API response data processed in
scripts/search.shand returned to the agent context. - Boundary markers: Absent. The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious directions embedded within the academic content.
- Capability inventory: The skill's capabilities are limited to network retrieval and display; it does not have the ability to write to the file system or execute commands based on the retrieved data.
- Sanitization: The skill does not perform sanitization or validation of the paper abstracts or titles before presenting them to the user.
Audit Metadata