naver-shopping-search

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches product data from a configurable proxy endpoint (defaulting to localhost) or directly from Naver's public JSON path (ns-portal.shopping.naver.com). These network operations are necessary for the skill's primary function of shopping search.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted product titles and descriptions from external search results.
  • Ingestion points: External product data is retrieved from Naver's public JSON API and processed within the skill workflow (SKILL.md).
  • Boundary markers: The skill does not explicitly define delimiters to isolate external text from agent instructions.
  • Capability inventory: The skill is limited to network GET requests for search purposes and does not have file-system write or code execution capabilities.
  • Sanitization: The instructions guide the agent to be "conservative" and to "normalize" candidates, providing a level of behavioral filtering for the processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 12:55 AM