aws-serverless
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides handler patterns that ingest external data from API Gateway events and SQS messages, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: Untrusted data enters the agent context via
event.bodyinhandler.jsandhandler.py, and throughrecord.bodyinprocessor.js. - Boundary markers: No explicit delimiters or boundary markers are utilized in the provided code snippets to separate external data from system instructions.
- Capability inventory: The skill identifies capabilities for interacting with AWS DynamoDB (GetCommand, Table.put/get) based on the ingested data.
- Sanitization: While the code uses standard JSON parsing, it lacks specific sanitization, escaping, or validation logic for the content of the ingested data before it is used in database operations.
Audit Metadata