log-analytics

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to ask for authentication (including username/password) and shows example MCP server env configs with OPENSEARCH_USERNAME/OPENSEARCH_PASSWORD placeholders, implying the agent will collect and insert secrets verbatim into configuration/commands, which creates an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to connect to a user-specified OpenSearch cluster and explicitly sample/index documents (e.g., "Sample Documents" / "Use SearchIndexTool ... head 5" and PPL/curl examples) so it will ingest and interpret arbitrary user-generated log content from third-party sources, which can materially influence queries and next actions.