cli-printing-press-generator

Warn

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a binary from a personal GitHub repository using the command go install github.com/mvanhorn/cli-printing-press/v4/cmd/printing-press@latest.
  • [EXTERNAL_DOWNLOADS]: The skill suggests cloning a repository from https://github.com/mvanhorn/cli-printing-press.git to obtain source code and supporting files.
  • [COMMAND_EXECUTION]: The skill's autonomous workflow includes a 'Verification' phase that executes 'live API smoke tests' and 'dogfood tests' on newly generated CLI binaries, which involves executing dynamically generated code.
  • [COMMAND_EXECUTION]: The tool provides manual commands such as printing-press verify and printing-press dogfood which facilitate the execution of the generated binaries on the local system.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted data from external websites and documentation during its research and discovery phases. Ingestion points: Processed documentation sites, community forums, and user-provided URLs during the research phase. Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions are identified. Capability inventory: The skill possesses the ability to write files, perform network requests, and execute generated code. Sanitization: There is no evidence of sanitization or validation of the retrieved content before it influences the code generation process.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 16, 2026, 11:23 PM