momentic-result-classification

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

• Third-party content exposure detected (high risk: 0.90). The skill requires the agent to inspect run assets returned by the MCP tools (e.g., momentic_get_run / momentic_get_step_result) which include before/after DOM snapshots (assets/.html), screenshots, HAR/network logs and other files captured from tested web pages—clearly ingesting untrusted third-party page content that can influence classification and next actions.