aws-ai
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides standard documentation and code samples for interacting with official AWS AI/ML services like Bedrock, SageMaker, and Rekognition. All ARNs and identifiers used in the examples are placeholders, following best practices for documentation.\n- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
amazon-q-developer-clipackage and references public GitHub repositories for SageMaker notebooks. These are well-known and trusted resources within the AWS development ecosystem.\n- [PROMPT_INJECTION]: The skill facilitates the processing of untrusted data from external sources, which presents a surface for indirect prompt injection.\n - Ingestion points: Data enters the context via S3 objects and local files passed to Rekognition, Transcribe, and Textract (SKILL.md).\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are included in the provided code examples.\n
- Capability inventory: The skill is configured with access to the
shell,read_file,write_file,glob, andgreptools (SKILL.md).\n - Sanitization: No input validation or sanitization of ingested content is performed before processing.
Audit Metadata