aci-change-deploy
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
python3to run local scripts defined by environment variables like$MCP_CALL,$ACI_MCP_SCRIPT, and$SERVICENOW_MCP_SCRIPT. This is the primary mechanism for interacting with ACI and ServiceNow tools. - [CREDENTIALS_UNSAFE]: The workflow passes credentials (
$ACI_USERNAME,$ACI_PASSWORD) as environment variables within shell command strings. While these are variables and not hardcoded secrets, passing them in shell strings can expose them to process monitors or command history logs. - [INDIRECT_PROMPT_INJECTION]: The agent's decision-making logic, such as whether to proceed with changes or initiate a rollback, depends on data ingested from external sources like ServiceNow (Change Request status) and Cisco APIC (fault counts and health scores).
- Ingestion points: Data returned by
get_change_request_details,faults, andhealthtools. - Boundary markers: No specific delimiters or safety instructions are provided to the agent to distinguish between trusted control data and potentially malicious content within CR descriptions or fault messages.
- Capability inventory: The skill possesses the ability to modify network policy (
tenants_post,fvAEPg_post, etc.) and update ServiceNow tickets. - Sanitization: The skill does not explicitly describe sanitization or validation of the data retrieved from ServiceNow or APIC before using it to drive logic.
Audit Metadata