pyats-linux-network

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides documentation and workflows for executing shell commands (e.g., ifconfig, ip route, netstat) on remote Linux hosts via the pyATS MCP script.
  • [PROMPT_INJECTION]: Indirect prompt injection (Category 8) vulnerability surface detected due to ingestion of untrusted remote host data.
  • Ingestion points: Output from remote Linux commands (ifconfig, ip route) enters the agent's context for diagnostic analysis.
  • Boundary markers: No specific delimiters or instructions to ignore embedded instructions within host output are present in the provided templates.
  • Capability inventory: The skill possesses the capability to execute commands on remote infrastructure and integrate with external source-of-truth platforms.
  • Sanitization: There is no evidence of sanitization or validation of the host output before it is processed by the agent for decision-making or reconciliation workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:32 AM