lyt-product-validation
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, including CSV/XLSX files, competitor links (e.g., 1688), and screenshots, creating a surface for indirect prompt injection.
- Ingestion points:
SKILL.mdandreferences/product-validation.mdconfirm the skill processes user-supplied tables and external web links. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within external data are defined in the instructions.
- Capability inventory: The skill performs data extraction and logical evaluation on external content to generate reports.
- Sanitization: No specific sanitization, filtering, or validation steps for ingested file content are documented.
Audit Metadata