customer-persona

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

• Third-party content exposure detected (low risk: 0.10). The skill workflow uses web search and AI generation tools (tavily/search-assistant, exa/search, exa/answer) to fetch market research data and user behavior insights from the open web.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill downloads and installs an executable CLI from an arbitrary third-party domain (inference.sh) via curl during setup/runtime, which constitutes a weak/unknown operational dependency.