pyats-config-mgmt

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes network management tasks and configuration commands via Python scripts defined by environment variables (e.g., $PYATS_MCP_SCRIPT). These operations are well-defined and align with the skill's purpose for network automation.\n- [EXTERNAL_DOWNLOADS]: No external downloads or remote script executions from untrusted sources were detected. All executable paths and configuration data are managed via local environment variables and established internal scripts.\n- [PROMPT_INJECTION]: The skill does not contain instructions that attempt to bypass safety filters or override agent constraints. It maintains a strict operational focus on configuration management workflows.\n- [DATA_EXFILTRATION]: While the skill accesses sensitive network configurations, it does so using local tools and environment variables without any patterns suggesting unauthorized data exfiltration to external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:31 AM