ata-trading-atlas

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

• Third-party content exposure detected (high risk: 0.90). The skill's documented workflow explicitly instructs the agent to query and read user-submitted, third-party "wisdom" records (e.g., GET /api/v1/wisdom/query and GET /api/v1/experiences/{record_id} described in SKILL.md and references/core-query-wisdom.md) and to consume community data sources (e.g., Yahoo Finance MCP get_stock_news in references/data-sources.md), so untrusted, user-generated content is fetched and used to shape decisions.