serverless-patterns
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified through data ingestion templates. (1) Ingestion points: Code examples in SKILL.md for SQS, S3, and API Gateway handlers process data from external event objects; (2) Boundary markers: No delimiters or protective markers are present in the code templates to separate data from instructions; (3) Capability inventory: The skill environment is configured with access to Bash, Read, and Edit tools; (4) Sanitization: The provided templates demonstrate basic JSON parsing but do not include explicit input validation or sanitization of the external content.
Audit Metadata