pyats-asa-firewall
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts to interact with network devices via the pyATS framework. This is the primary and intended purpose of the skill. Commands are structured to pass JSON-formatted parameters to a designated MCP script.
- [CREDENTIALS_UNSAFE]: The skill demonstrates safe credential handling by referencing environment variables (
%ENV{NETCLAW_USERNAME},%ENV{NETCLAW_PASSWORD}, etc.) within the pyATS testbed configuration rather than hardcoding sensitive information. - [DATA_EXFILTRATION]: No unauthorized network operations or access to sensitive local files were observed. The skill's network activity is limited to management of network infrastructure as described.
- [PROMPT_INJECTION]: The instructions follow standard operational guidelines and do not contain any patterns attempting to override agent safety filters or bypass system instructions.
- [SAFE]: The skill includes explicit guardrails emphasizing read-only operations and prohibiting configuration changes, which aligns with security best practices for automated infrastructure monitoring.
Audit Metadata