pyats-linux-network
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze output from diagnostic commands (e.g., ifconfig, ip route) executed on remote Linux hosts. * Ingestion points: Data enters the agent context through the output of pyats_run_linux_command across all workflow examples in SKILL.md. * Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious embedded content within device output. * Capability inventory: The agent has access to pyats_run_linux_command (shell command execution) and pyats_list_devices. * Sanitization: No evidence of sanitization, filtering, or escaping of the external command output before processing.
- [COMMAND_EXECUTION]: The skill provides patterns for executing shell commands on remote devices using the pyats_run_linux_command tool. * Evidence: Documentation in SKILL.md provides examples for running ifconfig, ip route show table all, route -n, and netstat -rn on hosts defined in a pyATS testbed.
Audit Metadata