wzrrd-publish
Fail
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill includes an instruction to install a CLI tool using a high-risk pattern where a remote shell script is downloaded from
https://wzrrd.sh/install.shand piped directly to the bash shell (curl -fsSL ... | bash). This provides the remote server with full control to execute arbitrary code on the host system. - [EXTERNAL_DOWNLOADS]: The skill initiates downloads from an external, non-trusted domain (
wzrrd.sh) to obtain executable scripts and service configurations. - [DATA_EXFILTRATION]: The primary function of the skill is to transfer local files or entire directory structures from the user's environment to an external third-party infrastructure (
wzrrd.sh). This constitutes a transfer of potentially sensitive local information to an external service. - [COMMAND_EXECUTION]: The skill directs the agent to execute several shell commands, including the
wzrrdtool for publishing data, authenticating accounts (wzrrd login), and running system environment checks (wzrrd doctor).
Recommendations
- HIGH: Downloads and executes remote code from: https://wzrrd.sh/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata