cisco-axl-cli
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
cisco-axlCLI via NPM and recommends optional packagesjson-variablesandcsv-parsefor bulk provisioning tasks. - [COMMAND_EXECUTION]: Operates by executing shell commands using the
cisco-axltool to perform administrative tasks, including CRUD operations, SQL queries, and dynamic AXL executions on CUCM clusters. - [PROMPT_INJECTION]: Evaluated for indirect prompt injection risks (Category 8).
- Ingestion points: Data is ingested from CUCM clusters via
get,list, andsql queryoperations inSKILL.md. - Boundary markers: None explicitly defined in instructions to delimit remote data from agent prompts.
- Capability inventory: The skill possesses powerful capabilities including
add,update,execute, andsql updateoperations across CUCM resources. - Sanitization: No specific sanitization or filtering of CUCM-sourced content is described.
- Risk Assessment: As an administrative tool for internal infrastructure, the surface for indirect injection is inherent to its primary purpose and carries minimal risk in standard operating environments.
Audit Metadata