Undetectable AI
v1.0.0Make AI text undetectable. TypeScript CLI that scans ChatGPT, Claude, OpenClaw output for patterns flagged by GPTZero, Turnitin, Originality.ai, then auto-fixes them to pass as human-written. Use to bypass AI detection, evade checkers, or humanize text before submission.
⭐ 5· 1.9k·4 current·4 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description (evade AI detectors) match the included code: analyze.ts, transform.ts, and patterns.json implement local regex-based detection and replacement. The skill does not contact external detectors (GPTZero/Turnitin/etc.) or require credentials; it just applies locally-stored patterns. The claim of scanning those third-party services is therefore an overstatement — it scans for patterns those services may flag, not the services themselves.
Instruction Scope
SKILL.md instructs the agent to run the included TypeScript scripts (npx ts-node ...) and to read/write local files; the scripts only read patterns.json and input files and write transformed output. There is no evidence in the instructions to read unrelated system files, environment variables, or to transmit data externally.
Install Mechanism
This is an instruction-only skill (no install spec), but SKILL.md tells users to run 'cd scripts && npm install'. The package.json is at the repository root, not inside scripts/, so the setup instruction is incorrect and could confuse users. The dependencies are standard devDeps (ts-node/typescript) from npm — expected for running the TypeScript scripts and not inherently suspicious.
Credentials
The skill requests no environment variables, credentials, or config paths and the code does not access any. This is proportionate for a local text-processing tool.
Persistence & Privilege
The skill does not request persistent/system-wide presence (always:false), does not modify other skills, and has no privileged operations. It runs only when invoked.
Assessment
This package is internally consistent: it performs local pattern matching and replacements to make text look less like typical LLM output. Before installing or running it, consider the following: (1) Ethical/legal risk — using tools to evade plagiarism or integrity checks can violate policies or laws; avoid using it to cheat or deceive. (2) Fix the setup instruction — run npm install at the repository root (where package.json lives) or move package.json into scripts/, otherwise ts-node will not be available. (3) Review patterns.json to ensure no sensitive phrases or private data will be altered/exposed. (4) Run the scripts in a disposable environment (not on sensitive documents) and inspect output before submitting elsewhere. (5) Because the tool operates locally and does not contact external services, network exfiltration is not indicated, but always review third-party dependencies and run npm install in a controlled environment.Like a lobster shell, security has layers — review code before you run it.
latestvk976c9etw8zber5444h8csr4xd80d7eg
License
MIT-0
Free to use, modify, and redistribute. No attribution required.