pyats-junos-routing

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes network diagnostic commands on Juniper devices via the pyats_run_show_command function. This is the primary intended function of the skill for network auditing.- [DATA_EXPOSURE]: The skill facilitates access to network operational data, including routing tables, neighbor adjacencies, and traffic engineering databases. While sensitive in a corporate context, this access is necessary for the skill's stated purpose of network monitoring.- [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface where untrusted data could influence command execution on network hardware.\n
  • Ingestion points: The device_name and command parameters in the pyats_run_show_command JSON payload within SKILL.md.\n
  • Boundary markers: No specific delimiters or safety instructions are defined in the skill to prevent the model from executing unauthorized JunOS commands.\n
  • Capability inventory: The skill possesses the capability to execute CLI commands on remote networking infrastructure.\n
  • Sanitization: No sanitization logic is present in the skill definition; the security of the operation relies on the underlying pyATS script implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 06:12 AM