aws-serverless

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for AWS Lambda handlers that ingest untrusted data from API Gateway events, such as event.body and event.pathParameters (SKILL.md). This creates a potential surface where malicious instructions embedded in the data could influence the agent if the data is processed as natural language instructions.\n
  • Ingestion points: SKILL.md (Lambda Handler Pattern and API Gateway Integration Pattern snippets)\n
  • Boundary markers: Absent in provided examples\n
  • Capability inventory: The skill demonstrates DynamoDB CRUD access and network communication via API Gateway\n
  • Sanitization: Basic validation like JSON parsing is used, but no specific prompt-injection sanitization is implemented.\n- [COMMAND_EXECUTION]: The skill includes instructions for infrastructure management using the AWS SAM CLI (sam build, sam deploy) and AWS CDK CLI (cdk deploy), which are standard for serverless deployment workflows.\n- [EXTERNAL_DOWNLOADS]: The skill references the installation of official developer tools (AWS SAM CLI and AWS CDK) from standard registries. These resources are provided by a well-known service (Amazon Web Services).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 08:10 AM
Security Audit — agent-trust-hub — aws-serverless