Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

AI Text Humanizer

Remove signs of AI-generated writing from text via the Claw0x API. Use when the user asks to humanize text, make AI writing sound natural, remove AI patterns...

MIT-0 · Free to use, modify, and redistribute. No attribution required.
0 · 23 · 0 current installs · 0 all-time installs
byclaw0x@kennyzir
MIT-0
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The skill's stated purpose (humanize AI text) aligns with its code: a primary LLM rewrite via Gemini and a deterministic regex fallback. However, registry metadata at the top lists no required env vars while SKILL.md declares CLAW0X_API_KEY and handler.ts requires both CLAW0X_API_KEY (for incoming auth) and GEMINI_API_KEY (to call Google's Generative API). The mismatch in declared vs required env vars is inconsistent and worth verifying.
Instruction Scope
SKILL.md instructs callers to POST to the Claw0x gateway with CLAW0X_API_KEY; the handler implements an authenticated POST endpoint and either forwards text to Google Gemini or runs local regex transforms. The instructions and code stay within the stated task. Important privacy note: user text will be sent to a third-party LLM (Google Generative API) when the LLM path is used; the documentation mentions Gemini but users should be aware of that external transmission.
Install Mechanism
No install spec (instruction-only runtime) and a single handler code file; nothing is downloaded from arbitrary URLs or written to disk by an installer. Low installation risk.
Credentials
SKILL.md requires a CLAW0X_API_KEY for gateway auth (reasonable). The handler also expects a GEMINI_API_KEY in the server environment to call the Google API; SKILL.md claims this is managed server-side, which is acceptable if true. The top-level registry metadata omits these env requirements — that inconsistency should be resolved. No unrelated credentials are requested.
Persistence & Privilege
The skill is not always-enabled and is user-invocable; it does not request system-wide config changes or other skills' credentials. Autonomous model invocation is allowed (default) but not combined with broad, unexplained credential access.
What to consider before installing
Before installing: (1) Confirm the CLAW0X_API_KEY requirement — the registry metadata omits it while SKILL.md requires it. (2) Understand that user text may be forwarded to Google Gemini (GEMINI_API_KEY is required server-side); do not send sensitive or regulated data unless you trust the operator and third-party processor. (3) Ask the publisher/operator where GEMINI_API_KEY is stored and who controls the Claw0x gateway; verify retention/logging policies. (4) Verify that the CLAW0X_API_KEY you provide is scoped appropriately and not reused elsewhere. (5) If anything in the registry or SKILL.md contradicts what the maintainer tells you, treat that as a red flag and request corrected metadata before deployment.
handler.ts:12
Environment variable access combined with network send.
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.

Like a lobster shell, security has layers — review code before you run it.

Current versionv1.0.0
Download zip
latestvk97e9chsp9fkbkxr9dbg80vpkn837gw3

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

SKILL.md

AI Text Humanizer

Rewrite AI-generated text to remove robotic patterns and make it sound naturally human. Targets 24 known AI writing signatures including filler phrases, AI vocabulary, sycophantic tone, and formulaic structure.

How It Works — Under the Hood

This skill uses a two-layer architecture to transform AI-generated text into human-sounding prose:

Layer 1: LLM Rewriting (Primary)

The primary path sends your text to a large language model (Gemini) with a carefully engineered system prompt derived from Wikipedia's WikiProject AI Cleanup guide. The LLM API key (GEMINI_API_KEY) is managed server-side by the Claw0x platform — callers do not need to provide or configure it. You only need a CLAW0X_API_KEY to authenticate through the Gateway. The system prompt instructs the model to:

  1. Scan the input for all 24 known AI writing patterns
  2. Rewrite the text to eliminate those patterns while preserving meaning
  3. Audit the rewritten output for any lingering AI-isms
  4. Revise a second time to catch patterns that survived the first pass

The LLM is also given personality rules: have opinions, vary sentence rhythm, acknowledge complexity, use "I" when natural, and let some structural imperfection through.

Layer 2: Regex Fallback (Deterministic)

If the LLM is unavailable (rate limit, timeout), the skill falls back to a deterministic regex engine that applies pattern-matched replacements across six categories:

  • Chatbot artifacts — removes "I hope this helps!", "Let me know if..."
  • Filler phrases — "in order to" → "to", "due to the fact that" → "because"
  • Significance inflation — "marking a pivotal moment" → removed
  • Copula avoidance — "serves as" → "is"
  • AI vocabulary — 40+ word substitutions (e.g. "leverage" → "use")
  • Emoji removal and em-dash normalization

The regex path is lower quality but instant, deterministic, and zero-cost.

Prerequisites

This skill requires a Claw0x API key:

  1. Sign up at claw0x.com
  2. Go to Dashboard → API Keys → Create Key
  3. Store the key securely using one of these methods:
    • Add CLAW0X_API_KEY to your agent's secure environment variables
    • Use your platform's secret manager (e.g. GitHub Secrets, Vercel env vars)
    • Use a .env file excluded from version control via .gitignore

Security note: Never embed API keys in prompts, source code, or version-controlled files.

When to Use

  • User says "humanize this", "make this sound more natural", "remove AI patterns"
  • User wants text to pass AI detection tools (GPTZero, Originality.ai, etc.)
  • Agent pipeline produces text that needs to sound human-written
  • Content teams need to clean up AI-drafted blog posts, emails, or documentation

API Call

curl -s -X POST https://claw0x.com/v1/call \
  -H "Authorization: Bearer $CLAW0X_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "skill": "humanizer",
    "input": {
      "text": "Your AI-generated text here..."
    }
  }'

Input

The input field accepts an object with one of these keys:

FieldTypeRequiredDescription
input.textstringyes (one of)Text to humanize
input.contentstringyes (one of)Alternative key for the text
input.bodystringyes (one of)Alternative key for the text

Output Fields

FieldTypeDescription
humanized_textstringThe rewritten text with AI patterns removed
original_lengthnumberCharacter count of original text
humanized_lengthnumberCharacter count of humanized text
methodstring"llm" (AI rewrite) or "regex" (deterministic fallback)

Example

Input:

{
  "skill": "humanizer",
  "input": {
    "text": "Additionally, it is worth noting that this groundbreaking solution serves as a testament to the transformative power of innovation. The future looks bright for this pivotal technology. I hope this helps!"
  }
}

Output:

{
  "humanized_text": "This solution shows what good engineering looks like in practice. The technology has real potential, though how it plays out depends on adoption.",
  "original_length": 204,
  "humanized_length": 138,
  "method": "llm"
}

Error Codes

  • 400 — Missing or empty text input
  • 500 — Processing failed (not billed)

Pricing

Pay-per-successful-call only. Failed calls and 5xx errors are never charged.

Files

2 total
Select a file
Select a file to preview.

Comments

Loading comments…