pyats-junos-interfaces

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of operational JunOS CLI commands (e.g., 'show interfaces', 'show lacp', 'show arp') on network devices through the pyats_run_show_command tool.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing untrusted data from network devices, such as interface descriptions and LLDP neighbor chassis IDs.
  • Ingestion points: Data returned from the JunOS device commands listed in SKILL.md.
  • Boundary markers: Absent; the skill does not utilize delimiters or specific instructions to ignore embedded content within device outputs.
  • Capability inventory: Subprocess execution through $MCP_CALL and python3 as defined in the metadata and examples in SKILL.md.
  • Sanitization: Absent; the skill lacks explicit validation or escaping of the ingested device operational data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:31 AM