infra-architect
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override agent behavior were found.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or unauthorized data access patterns detected. The IAM and S3 examples use placeholder values and dummy account IDs.
- [Remote Code Execution] (SAFE): The skill does not perform any network operations, download external scripts, or execute shell commands.
- [Indirect Prompt Injection] (SAFE): 1. Ingestion points: User input for infrastructure requests. 2. Boundary markers: None. 3. Capability inventory: No execution capabilities detected (text/code output only). 4. Sanitization: Relies on the agent's internal safety guardrails for output generation.
Audit Metadata