skills/tomz/agent-skills/aws-ai/Gen Agent Trust Hub

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-cli package 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, and grep tools (SKILL.md).\n
  • Sanitization: No input validation or sanitization of ingested content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 05:07 PM
Security Audit — agent-trust-hub — aws-ai