pyats-junos-system

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a shell command to invoke local Python processes via the $MCP_CALL and $PYATS_MCP_SCRIPT environment variables to communicate with Juniper network devices.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8).
  • Ingestion points: The agent processes operational data and logs from Juniper devices (e.g., 'show log messages', 'show system users') as defined in SKILL.md.
  • Boundary markers: No specific delimiters or 'ignore' instructions are provided to separate device output from agent instructions.
  • Capability inventory: The skill allows the execution of shell-based Python scripts and SSH-based network operations.
  • Sanitization: No evidence of input validation or output escaping is found for data returned from the devices before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:31 AM