agency-developer-advocate

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

• Third-party content exposure detected (high risk: 0.85). The required workflow includes “Read every GitHub issue opened in the last 30 days” and “Review social media mentions and Discord/Slack for unfiltered sentiment,” which at runtime would ingest outsider-authored free-form text from those third-party sources into the agent’s LLM context.