pp-adminbyrequest
Fail
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [DATA_EXFILTRATION]: The
adminbyrequest-pp-clitool features a--deliver webhook:<url>flag, which enables the agent to POST command outputs directly to an external HTTP endpoint. This capability can be used to exfiltrate sensitive administrative data such as audit logs, event details, and elevation request reasons to any destination. - [DATA_EXFILTRATION]: The
--deliver file:<path>flag allows the tool to write its output to any specified file path. This represents a risk of writing sensitive information to unauthorized locations or potentially overwriting critical system files. - [EXTERNAL_DOWNLOADS]: The skill documentation provides instructions for installing the CLI tool via
npxfrom the@mvanhornregistry and viago installfrom a GitHub repository. These methods involve downloading code from external sources during the skill's setup phase. - [REMOTE_CODE_EXECUTION]: The installation steps provided in the skill execute remote packages and binaries (
npxandgo install) to provision the environment. While these resources originate from the vendor's infrastructure, they constitute the execution of remote code. - [COMMAND_EXECUTION]: The skill facilitates the execution of numerous administrative commands through a CLI binary, including sensitive operations like approving or denying elevation requests and generating offline security PINs for endpoints.
Recommendations
- AI detected serious security threats
Audit Metadata