clab-lab-management
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes an
execCommandtool designed to run commands on containerized lab nodes. This is a core functionality for network lab management and is restricted to the managed lab environment. - [PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection via the topology JSON and command execution tools. 1. Ingestion points:
deployLab(topologyContent) andexecCommand(command). 2. Boundary markers: The documentation does not specify the use of delimiters or boundary instructions for processing these inputs. 3. Capability inventory: The skill can execute commands on nodes and manage lab infrastructure. 4. Sanitization: No sanitization or input validation mechanisms are described in the markdown. - [CREDENTIALS_UNSAFE]: The skill requires API authentication but follows security best practices by utilizing environment variables (
CLAB_API_USERNAME,CLAB_API_PASSWORD) rather than hardcoding sensitive credentials.
Audit Metadata