hm-research

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the required workflow calls Crawlora’s H&M endpoints with user-supplied free-text fields (e.g., hm_search uses query, and other endpoints accept free-text like hm_stores.search) and the skill ingests the resulting JSON including customer review text from H&M into the LLM context.