setup-agent-scanner

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires creating a connection with authParameters containing credentials (e.g., accessKeyId/secretAccessKey) and marks the requestBody as userProvided, which would force the agent to include secret values verbatim in API requests or generated payloads.

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly configures a scanner to discover and import AI agents from external cloud platforms (e.g., "discover AI agents from external platforms like AWS Bedrock, Microsoft Copilot, or Google Vertex AI" and the createScanConfigurations step using the Agent Scanner Configuration API), meaning it fetches and ingests third‑party agent content that could contain user-generated instructions influencing behavior.