pp-human-goat

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill operates by executing a local binary named human-goat-pp-cli. This tool is used for all primary functions, including hiring labor, checking task status, and managing account configuration.
  • [EXTERNAL_DOWNLOADS]: To function, the skill requires the installation of external components from the author's public repositories. This includes a Go module (github.com/mvanhorn/printing-press-library) and an npm package (@mvanhorn/printing-press-library).
  • [PROMPT_INJECTION]: The skill processes untrusted data from external sources, specifically tasker biographies, reviews, and errand statuses from the TaskRabbit and Magic networks. This creates a surface for indirect prompt injection if these external data points contain malicious instructions aimed at the agent's execution logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 06:06 PM
Security Audit — agent-trust-hub — pp-human-goat