pyats-linux-system
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides the
pyats_run_linux_commandtool, which allows the agent to execute shell commands on remote Linux hosts defined in a pyATS testbed. This enables high-privilege operations such as process management and system inspection.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (remote Linux systems) that could be under the control of an adversary, posing a risk of indirect prompt injection.\n - Ingestion points: The output of system commands like
ps -ef,ls -l, anddocker statsis returned to the agent context.\n - Boundary markers: There are no boundary markers or explicit instructions to the agent to treat the remote command output as untrusted or to ignore embedded instructions.\n
- Capability inventory: The skill possesses the capability to execute commands and read files on remote hosts, which could be abused if the agent follows instructions hidden in the command output.\n
- Sanitization: The skill lacks mechanisms to sanitize, validate, or filter the content returned from remote system calls before processing it.
Audit Metadata