aws-security
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- Command Execution: The skill facilitates the use of AWS CLI commands for security auditing. It strictly uses non-mutating APIs (read-only) to ensure environment safety. The use of these commands is consistent with the primary purpose of managing AWS infrastructure.
- Indirect Prompt Injection Surface: The skill ingests data from external AWS APIs (e.g., findings in GuardDuty and Security Hub), creating an attack surface for indirect prompt injection. However, the risk is minimized by instructions to summarize findings before presenting raw data, providing a user-mediated verification step. The skill lacks hazardous capabilities like file-writing or network exfiltration.
- Trusted Documentation Sources: The skill references official AWS documentation for API schemas and best practices. These sources are well-known and trusted service providers, presenting no security risk in this context.
Audit Metadata