pyats-config-mgmt

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands by constructing strings that invoke Python scripts using environment variables like $MCP_CALL and $PYATS_MCP_SCRIPT. These variables serve as dynamic paths for internal tool invocation within the agent's operating environment.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes external input for network operations.
  • Ingestion points: The variables device_name, command, and config_commands are used to build JSON payloads for tool calls across SKILL.md.
  • Boundary markers: No explicit delimiters or boundary markers are used to separate user-provided commands from the execution context in the provided examples.
  • Capability inventory: The skill possesses high-privilege capabilities including pyats_configure_device (configuration changes), pyats_run_show_command (state inspection), and interaction with ServiceNow and GAIT for record management.
  • Sanitization: No sanitization, filtering, or validation logic is defined for the input strings before they are passed to the underlying network interaction tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 06:12 AM