paw-cra-agent-strategist

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

• Third-party content exposure detected (high risk: 0.90). The skill's research workflows explicitly instruct the agent to load and scrape public social media and websites (e.g., agent-browser in references/browser-tools.md for Instagram/TikTok/LinkedIn and web_search_exa / crawling_exa in references and autonomous-wake.md) and then ingest and synthesize that untrusted, user-generated content into reports and recommendations, which can directly influence subsequent decisions and actions.