auditing-gcp-iam-permissions
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a legitimate security tool for auditing Google Cloud IAM configurations. The scripts and instructions provided align with industry best practices for cloud security assessments.
- [EXTERNAL_DOWNLOADS]: The skill depends on official and trusted Python libraries from Google, specifically
google-cloud-asset,google-cloud-resource-manager, andgoogle-cloud-iam. These are well-known packages from a trusted organization. - [COMMAND_EXECUTION]: The workflow incorporates standard
gcloudCLI commands to list and manage IAM policies. These commands are used for their intended administrative purposes and do not involve untrusted input or malicious execution patterns. - [DATA_EXFILTRATION]: While the skill accesses sensitive IAM policy data, this is required for its auditing function. The data is processed locally and stored in a JSON file (
gcp_iam_audit.json), with no evidence of exfiltration to external domains. - [INDIRECT_PROMPT_INJECTION]: The skill processes IAM policy data which is technically an external source. While this creates a theoretical attack surface, it is a necessary component of the skill's auditing function, and no specific exploitable patterns were identified in the data processing logic.
Audit Metadata