pitch-deck-agent

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly asks for external "Website URL" or existing materials (Q8) and instructs using brand-research-agent, market-researcher-agent, and competitive-intel-agent to extract and use data from third-party sites/open web, so the agent will ingest and interpret untrusted public content as part of its workflow.