cisco-ucce-cli

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the user to install the 'cisco-ucce' package from the NPM registry or execute it using 'npx'. These are vendor-provided resources used for the skill's primary function.
  • [COMMAND_EXECUTION]: Executes various 'cisco-ucce' CLI commands to perform system diagnostics, health checks, and log collection. It supports an '--insecure' flag which skips TLS certificate verification for API calls.
  • [PROMPT_INJECTION]: Identified an indirect prompt injection surface where the tool ingests data from external Cisco UCCE API services (AW, Finesse, CVP, VVB).
  • Ingestion points: API responses from services like Finesse (agent states, teams) and the Diagnostic Portal.
  • Boundary markers: The skill does not define delimiters or instructions to ignore embedded instructions in the command output.
  • Capability inventory: The skill can perform network requests, file system writes (log/trace downloads), and configuration management.
  • Sanitization: No evidence of validation or sanitization of content retrieved from the Cisco APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 11:41 PM