aws-serverless
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements patterns that ingest untrusted data from external sources, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: The Lambda handler patterns in
SKILL.mdingest data fromevent.body(API Gateway) andrecord.body(SQS messages). - Boundary markers: No boundary markers or instructions to ignore embedded commands are present in the provided templates.
- Capability inventory: The skill utilizes
docClient.send(AWS SDK) for DynamoDB operations, enabling the agent to read/write data based on the processed input. - Sanitization: The provided code snippets perform
JSON.parse()on inputs but do not include validation or sanitization logic to filter potential malicious instructions embedded in the JSON payloads.
Audit Metadata