skills/mukul975/anthropic-cybersecurity-skills/implementing-aws-iam-permission-boundaries/Gen Agent Trust Hub
implementing-aws-iam-permission-boundaries
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill offers legitimate security implementation tools and educational content regarding AWS Identity and Access Management (IAM). No signs of prompt injection, persistence, or malicious behavior were found.- [COMMAND_EXECUTION]: The Python scripts (
scripts/agent.pyandscripts/process.py) use theboto3library to interact with the AWS IAM service. These scripts facilitate administrative tasks like listing roles and creating policies within the user's own AWS environment.- [EXTERNAL_DOWNLOADS]: The skill references established documentation from AWS and official sample repositories on GitHub. It does not perform any unverified remote script execution or downloads from untrusted sources.
Audit Metadata