pyats-linux-network

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of diagnostic shell commands such as ifconfig, ip, route, and netstat on remote Linux hosts via the pyats_run_linux_command tool. The skill documentation emphasizes read-only operations and includes guardrails to prevent configuration changes.- [PROMPT_INJECTION]: Indirect prompt injection surface identified as the agent ingests and processes text output from remote network devices without explicit sanitization or boundary markers.
  • Ingestion points: Output from remote Linux hosts retrieved via pyats_run_linux_command during workflow execution.
  • Boundary markers: Absent; there are no instructions to the agent to ignore or delimit embedded instructions within device output.
  • Capability inventory: The skill has the capability to execute further shell commands on any device within the pyATS testbed using pyats_run_linux_command.
  • Sanitization: Absent; the skill does not specify any filtering or validation of the data returned from remote hosts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 06:12 AM