pp-azure-functions-admin
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to install the
azure-functions-admin-pp-cliand an MCP server from NPM (@mvanhorn/printing-press-library) and GitHub (github.com/mvanhorn/printing-press-library). These are external dependencies hosted on public platforms under the vendor's namespace. - [COMMAND_EXECUTION]: The skill defines several commands to be executed via the system shell, providing the agent with the ability to query Azure infrastructure, hosting plans, and application settings.
- [DATA_EXFILTRATION]: The CLI tool includes a
--deliver webhook:<url>parameter which enables the transmission of command outputs to arbitrary remote URLs. Additionally, the tool features a feedback mechanism that can be configured via environment variables (AZURE_FUNCTIONS_ADMIN_FEEDBACK_AUTO_SEND) to automatically exfiltrate local feedback data to a remote endpoint. - [PROMPT_INJECTION]: The skill processes external data from Azure subscription metadata and application settings. While the
--agentflag enforces JSON formatting to provide data boundaries, there is a risk that malicious content within these Azure resources could influence the agent's behavior. The tool identifies that some settings might be masked to prevent credential exposure in the logs.
Audit Metadata