agency-trend-researcher

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

• Third-party content exposure detected (high risk: 1.00). This skill's SKILL.md explicitly requires automated monitoring and signal collection from public, user-generated sources—e.g., "Data Sources: Social media trends... blog posts, forums, community discussions" and "Signal Collection: Automated monitoring across 50+ sources"—so the agent ingests untrusted third-party content that can influence its actions.