marketing-studio-agent

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow includes Playwright “Product demo” capture of a live URL (feeders/capture/capture.mjs --url ...), which can ingest outsider-authored page text (public web content) into the agent/LLM context via browser-extracted content during runtime.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's installation instructs cloning and then running code from the remote repository (git clone https://github.com/ucsandman/marketing-studio.git), which fetches and causes execution of external code required by the skill.