market-kurly-search

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The agent searches external product listings and web pages on Market Kurly via public API endpoints and product detail pages, which constitutes low-risk ingestion of outsider-authored search results and web content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs runtime execution of npx commands fetching @nomadamas/k-skill, which represents an external dependency with common/reputable unofficial provenance.