Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
De-AI-fy Text Skill1.0.0
v1.0.1Remove AI-like features from text to make it more natural and human-like (去除AI生成文本的AI特征，使文本更自然、更接近人类写作)
⭐ 0· 384·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (remove AI-like features / humanize text) match the included code and config: AITextDetector, TextHumanizer, DeAIProcessor and rules.json provide detection and replacement rules for Chinese and English. No unrelated binaries, env vars, or credentials are requested.
Instruction Scope
SKILL.md describes local Python API and CLI usage and references only rules.json and local input/output files. The instructions do not ask the agent to read unrelated system files, access secrets, or send data to external endpoints.
Install Mechanism
No install spec is present (instruction-only at registry level) and the package is provided as source files. There are no downloads or third‑party install steps embedded in the skill that would write or execute remote code.
Credentials
The skill requires no environment variables, credentials, or config paths. The only optional dependency is jieba for better Chinese tokenization, which is local and documented. No unrelated secrets are requested.
Persistence & Privilege
Flags show always:false and user-invocable:true. The skill does not request permanent platform-wide privileges, nor does it modify other skills or system-wide settings.
Assessment
What you should consider before installing: 1) This is a local, rules-based text processing library (no network calls or secret access detected) — good for privacy, but review rules.json because substitutions can change meaning; test on non-sensitive samples first. 2) The project optionally uses jieba for Chinese tokenization — install only if you want improved Chinese handling. 3) Run the included unit tests (python test_deai.py) and examples in a sandbox to verify behavior with your real data. 4) If you will use it on sensitive/regulated text, manually review the transformation rules and outputs because automated replacements may unintentionally alter legal/medical/financial meaning. 5) If you plan production use, pin the source (or vendor it) and periodically review the repository for updates or changes.Like a lobster shell, security has layers — review code before you run it.
latestvk971mqtfyq1v1gnwnfvscw5g2d822wk1latest Changelogvk979zgf38661esg8v2datvh3cx8221bn
License
MIT-0
Free to use, modify, and redistribute. No attribution required.