cloud-architect
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates the
fetchtool to retrieve external web content and utilizes MCP servers that interact with external knowledge bases. This configuration creates an attack surface where instructions embedded in external resources could potentially influence the agent's outputs, such as AWS CLI commands or CDK code. - Ingestion points: The
fetchtool is used to retrieve content from arbitrary URLs, and theawsknowledgeserver retrieves data from an external API. - Boundary markers: The instructions do not define clear boundaries or provide guidance for the agent to treat external content as untrusted data.
- Capability inventory: The skill possesses the capability to suggest AWS CLI commands through the
awsapitool and generate infrastructure-as-code (CDK). - Sanitization: There is no evidence of content sanitization or validation before the agent processes external data.
Audit Metadata