aci-change-deploy
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands to invoke local automation scripts defined by environment variables ($ACI_MCP_SCRIPT, $SERVICENOW_MCP_SCRIPT, $GAIT_MCP_SCRIPT). These scripts are used to perform all fabric operations and change management tasks as intended for this automation use case.
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingests and processes data from external systems (ServiceNow and APIC).
- Ingestion points: Data enters the context via ServiceNow tool outputs (change details, status) and APIC tool outputs (fault counts, health scores, tenant lists).
- Boundary markers: No explicit delimiters or "ignore embedded instructions" markers are present in the command templates.
- Capability inventory: The agent has the capability to execute administrative commands on the network fabric using provided credentials.
- Sanitization: No explicit validation or filtering of the external data is documented before use in decision-making logic.
- [SAFE]: The implementation follows a strict operational lifecycle including approval gates and automated health checks, which significantly reduces the risk of accidental or unauthorized network changes.
Audit Metadata