aws-serverless
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface detected.\n
- Ingestion points: The skill processes untrusted data from
event.bodyand SQSevent.RecordsinSKILL.md.\n - Boundary markers: No delimiters or instructions to ignore embedded commands are used when handling external event data.\n
- Capability inventory: The code snippets perform database writes and reads (
docClient.send,saveToDatabase) based on the content of the ingested event data.\n - Sanitization: The logic lacks input validation or sanitization before processing the parsed JSON data.\n- [SAFE]: The skill uses official and trusted AWS SDKs for Node.js (
@aws-sdk/*) and Python (boto3).\n- [SAFE]: SAM templates demonstrate best practices by using resource-scoped IAM policies (DynamoDBReadPolicy,DynamoDBCrudPolicy) rather than wildcard permissions.
Audit Metadata