iam
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The content consists of educational documentation and standard technical examples without any attempts to manipulate agent behavior.
- [Data Exposure & Exfiltration] (SAFE): No sensitive local data is targeted. Network interactions are restricted to standard AWS API usage via CLI and SDK. Example ARNs and account IDs are used for documentation purposes.
- [Obfuscation] (SAFE): The files use plain text and standard formatting. No hidden or encoded content was found. The use of 'base64 -d' in a CLI example is a standard administrative procedure for AWS credential reports.
- [External Downloads] (SAFE): No external scripts or packages are downloaded. References are limited to official AWS documentation and standard SDKs.
- [Command Execution] (SAFE): Command examples are restricted to AWS service management (IAM, CloudWatch, CloudTrail), which is the intended purpose of the skill. No unauthorized local command execution was detected.
Audit Metadata