xy-selection
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches diagnostic reference data (referred to as "atoms") from the vendor's official API at
https://api.xyskill.xyz. This is used to provide evidence-based case studies and business principles during the diagnostic process. - [COMMAND_EXECUTION]: The skill invokes a local Python utility script (
atoms-search.py) included with the skill package to query the knowledge base. The script is used for processing search keywords and retrieving relevant data entries. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted user input describing product categories and business scenarios in Phase 1 and Phase 2. Boundary markers to delimit user input are absent, and the capability inventory includes local script execution via
atoms-search.py. No explicit sanitization or filtering of the user-provided data is performed before it is interpolated into diagnostic prompts, though the risk is limited to the scope of report generation.
Audit Metadata