exploring-data-catalog
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various AWS CLI commands (
aws glue,aws s3tables,aws sts) to perform its discovery tasks. These operations are scoped to metadata retrieval and identity verification. - [SAFE]: The skill explicitly identifies that AWS Glue catalog content (descriptions, forms, glossary text) is untrusted data and instructs the agent to ignore any embedded instructions. This directly mitigates indirect prompt injection risks.
- [SAFE]: The skill mandates shell-quoting for all user-provided values when constructing CLI commands, which prevents command injection vulnerabilities.
- [SAFE]: No obfuscation, hardcoded credentials, or unauthorized network exfiltration patterns were detected. The skill's operations are consistent with its stated purpose of data catalog discovery.
Audit Metadata