commerce-app-webhooks
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
aio app buildto validate configurations andnpx @adobe/aio-commerce-lib-app initto scaffold the project. These are official tools provided by the vendor (Adobe) to manage Commerce App extensions. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs to generate configuration entries in
app.commerce.config.tsandext.config.yaml. - Ingestion points: Data enters via the user prompt (intent) and by reading the existing
app.commerce.config.tsfile. - Boundary markers: The skill uses a structured 'Derive config values' step to validate data before injection.
- Capability inventory: The skill can write files and execute local shell commands (
aio,npx). - Sanitization: The skill enforces strict regex validation (
[a-zA-Z0-9_]+) for identifiers likebatch_nameandhook_nameto prevent injection into the configuration schema. - [DYNAMIC_EXECUTION]: The skill generates a source code skeleton for Node.js actions (handlers). This is a standard template-based code generation practice for developer productivity tools and does not involve untrusted data in the execution path of the generator itself.
Audit Metadata