pyats-linux-vmware
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
pyats_run_linux_commandtool to execute administrativevim-cmdoperations on VMware ESXi hosts. This is the primary intended function of the skill for VM inventory and snapshot inspection (SKILL.md). - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the processing of hypervisor data.
- Ingestion points: The skill ingests and parses output from the ESXi host via the
vim-cmdcommand, specifically processing VM names, VMX file paths, and VM annotations (SKILL.md). - Boundary markers: No explicit boundary markers or delimiters are used to wrap the untrusted host output to prevent it from being interpreted as instructions by the agent.
- Capability inventory: The agent has the capability to execute commands on remote devices in the testbed using
pyats_run_linux_command(SKILL.md). - Sanitization: The skill does not implement validation or sanitization of the VM metadata before displaying it or using it in workflows.
Audit Metadata