aws-well-architected
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from the NPM registry and utilizesnpxto execute the latest version of the tool. These are official resources provided by the vendor (membranedev) to facilitate platform integration. - [COMMAND_EXECUTION]: The skill uses the
membraneCLI to perform operations such aslogin,connect, andaction run. It also provides amembrane requestcommand that acts as a proxy for the AWS Well-Architected API, allowing for custom API interactions while automatically handling authentication headers and credential refreshes. - [INDIRECT_PROMPT_INJECTION]: The skill processes structured data from AWS Well-Architected through actions and API proxy requests.
- Ingestion points: Data enters the agent context via
membrane action list(action schemas) andmembrane action run(action execution results). - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided in the skill text.
- Capability inventory: The skill possesses the ability to execute CLI commands and perform network requests via the
membraneproxy tool. - Sanitization: The skill does not specify any sanitization or validation logic for the data retrieved from external API endpoints.
Audit Metadata