naver-shopping-search
Warn
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill mandates the execution of
npx -y @nomadamas/k-skill@0as a primary step to obtain instructions and manage helper files. This pattern involves downloading and running code from an external registry (npm) at runtime. - [EXTERNAL_DOWNLOADS]: The skill relies on external resources, including a proxy server at
k-skill-proxy.nomadamas.orgfor data retrieval and the npm registry for its CLI dependencies. - [COMMAND_EXECUTION]: The instructions involve executing shell commands such as
npxandcurlto interact with external services and tools. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted product metadata retrieved from external search results, which could theoretically contain malicious instructions designed to influence the agent.
- Ingestion points: Product search results (titles, mall names, prices) fetched from
https://k-skill-proxy.nomadamas.org/v1/naver-shopping/search(instruction.md). - Boundary markers: The skill does not define explicit delimiters or instructions to ignore potential commands embedded within the fetched product data.
- Capability inventory: The skill possesses shell execution capabilities (
npx) and network access (curl) (SKILL.md, instruction.md). - Sanitization: There is no evidence of sanitization or filtering of the ingested product titles or descriptions before they are presented to the agent.
Audit Metadata