Skip to content
blader organisation mark

humanizer

blader/humanizer

Scanned · findings(2)Skills

Agent skill that removes signs of AI-generated writing from text

Install

A skill is a folder of written instructions your AI agent reads when it needs them. Installing one copies those files into your agent’s skills directory. Nothing runs. More about skills.

Not available through Techandria. Techandria only installs commits a person has approved. This one has not been.

You can still get the code from the source and read it yourself:

git clone https://github.com/blader/humanizer

What we checked

Scanned · findings(2)

The scans completed and turned something up. The findings are listed below in plain English; nothing here has been approved for install.

  • Source and instructions

    Read every text file for prompt injection, hidden instructions, dangerous commands and exposed credentials

  • Exposed secrets

    Scanned the whole repository for committed API keys, tokens and private keys

  • Suspicious code

    Ran static analysis rules over the Python, JavaScript and TypeScript source

  • Skill instructions

    Analysed any agent skill definitions against Cisco’s scanner

  • Malware

    Scanned the archive with ClamAV using signatures no more than 24 hours old

  • Dependency advisories

    Looked up every pinned dependency against the OSV vulnerability database

  • Runtime behaviour

    No runtime test was run for this project

What we found (2)

  • MediumCarries a data file an agent reads but you would not see

    A configuration or manifest in a dot-directory that shapes agent behaviour without appearing in the README. Usually ordinary plugin packaging; shown because it is invisible otherwise.

    .claude-plugin/marketplace.json · Cisco Skill Scanner

  • MediumCarries a data file an agent reads but you would not see

    A configuration or manifest in a dot-directory that shapes agent behaviour without appearing in the README. Usually ordinary plugin packaging; shown because it is invisible otherwise.

    .claude-plugin/plugin.json · Cisco Skill Scanner

Commit reviewed
9862685f575c
Scanned
Sep 11, 2026
Freshness
Evidence has expired and needs a fresh scan
Maintain this project? Add the review badge to your README

The badge shows this project's current review state and updates on its own — including if the state changes. It links back to this page.

Techandria review status for blader/humanizer
[![Techandria](https://techandria.com/badge/blader/humanizer.svg)](https://techandria.com/project/blader/humanizer)

Read the full scan report — hashes, tool versions, coverage gaps and the raw findings. What we check, and what we cannot.

README

No README could be fetched from GitHub for this repository.

More in Skills

wshobson organisation mark

agents

wshobson/agents

Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity

Pushed 2 days ago.MIT LicensePythonPlugins42.1k+283
addyosmani organisation mark

agent-skills

addyosmani/agent-skills

Production-grade engineering skills for AI coding agents.

Pushed 2 days ago.MIT LicenseJavaScriptSkills113.0k+2.0k
zenstory-ai organisation mark

oh-story-claudecode

zenstory-ai/oh-story-claudecode

网文/小说写作 skill 包,覆盖长篇与短篇网络小说的扫榜、拆文、写作、去AI味、封面图全流程 | An all-in-one skill pack for long- and short-form web fiction.

Pushed 2 days ago.MIT LicenseJavaScriptSkills8.3k+234
OthmanAdi organisation mark

planning-with-files

OthmanAdi/planning-with-files

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.

Pushed yesterday.MIT LicensePythonPlugins27.9k+158