pp-digitalocean

Warn

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires downloading and installing the digitalocean-pp-cli binary using npx -y @mvanhorn/printing-press and go install from the author's repository at github.com/mvanhorn/printing-press-library.
  • [REMOTE_CODE_EXECUTION]: The installation instructions involve executing code directly from remote sources (NPM and GitHub), which enables the execution of externally hosted software on the local system.
  • [DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> option that routes command results to an arbitrary URL. This feature, along with the feedback command's ability to send data to a remote endpoint, creates a significant pathway for exfiltrating sensitive cloud configuration and resource data.
  • [COMMAND_EXECUTION]: User-provided arguments are passed directly to shell commands (digitalocean-pp-cli $ARGUMENTS), which could lead to command injection if the input is not properly validated.
  • [CREDENTIALS_UNSAFE]: The skill instructs users to set authentication tokens using command-line arguments (auth set-token YOUR_TOKEN_HERE), a practice that can expose sensitive secrets in shell history or process logs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 10, 2026, 07:52 AM