Back to plugin

Security audit

HumanizeAI

Security checks for vulnerabilities and agentic risk

Overview

The skill's code, docs, and runtime instructions are consistent: it performs local, deterministic text rewrites, asks for no credentials, and contains no network calls or unexpected file/system access.

This plugin appears coherent and low-risk: it performs only local text rewrites and requests no credentials. Before installing, consider: (1) review the code if you plan to send sensitive secrets through it (it runs in-process and could see any text you pass); (2) installation will pull a small npm dependency (zod) — if your environment forbids external registry access, install from a vetted offline package; (3) enabling debug mode logs replacement counts to stdout (no network exfiltration). If those points are acceptable, the skill matches its description.

Static analysis

No suspicious patterns detected.