bmad-agent-marketing-sales

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires live web research: SKILL.md lists agent-browser as a dependency and references/competitive-research.md contains concrete agent-browser commands to open and "get text body" from public competitor pages (pricing pages, Google search results), user-generated review sites (G2/Capterra), and LinkedIn ad library — the agent is expected to ingest and act on that untrusted third‑party content to build battle cards, comparisons, and champion kits, creating a clear risk of indirect prompt injection.