Skills
Navigate
skills/automateyournetwork/netclaw/clab-lab-management/Gen Agent Trust Hub

clab-lab-management

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of topology definitions and command strings, which represents a surface for indirect prompt injection.
  • Ingestion points: The deployLab tool ingests topologyContent JSON objects, and execCommand ingests raw command strings (SKILL.md).
  • Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the processed data.
  • Capability inventory: The skill has the capability to deploy containerized infrastructure and execute shell-like commands on nodes via the ContainerLab API (SKILL.md).
  • Sanitization: No sanitization or validation mechanisms are mentioned for the incoming JSON objects or command strings.
  • [COMMAND_EXECUTION]: The skill provides tools to execute arbitrary commands on containerized network nodes within the managed lab environment.
  • Evidence: The execCommand tool allows the agent to run commands on specific nodes or all nodes in a named lab (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 03:55 PM