alterlab-pra-brand-analyst

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md Agentic Protocol and Workflow explicitly instruct the agent to "Search the web for current brand perception data, competitor positioning statements, and market reports" and to "cross-reference web research findings," meaning it ingests open/public third-party content (e.g., web pages, social/media/market reports) which the agent must read and use to drive analysis and recommendations.