Detector AI
v1.0.0AI Detection Tool - Detect AI-generated text with multiple analysis methods including perplexity analysis, burstiness detection, readability scoring, and AI...
⭐ 0· 49·0 current·0 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 (AI detection) match the included artifacts: SKILL.md describes detection methods and the repository contains a detector script and a patterns reference. No unrelated services, credentials, or binaries are requested.
Instruction Scope
SKILL.md instructs the agent to ask the user for text, run the included script, and interpret results — all within the stated purpose. The instructions do not ask the agent to read unrelated files, system config, or transmit results to external endpoints.
Install Mechanism
No install spec (instruction-only) which is low risk. The skill includes a local Python script (detect_ai.py) intended to be executed; running included code writes nothing to disk beyond execution. However, the provided detect_ai.py content in the submission is truncated, so the remainder of the script could not be inspected.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The visible portion of the script imports only standard libs and performs local text analysis, which is proportional to its purpose.
Persistence & Privilege
The skill is not marked always:true and does not request special privileges. It is user-invocable and can be invoked by the agent (platform default). There is no evidence it modifies other skills or system-wide settings.
Assessment
This skill appears to do what it says: a local heuristic detector that uses perplexity, burstiness, readability, and fingerprint rules. Before installing: (1) request the complete detect_ai.py file (the submission truncated it) and verify the remainder contains no network, subprocess, os.path, or credential-access code; (2) remember the tool is heuristic — results are not definitive and can be wrong; avoid submitting highly sensitive text unless you confirm the script runs fully offline; (3) if you plan to run it on this platform, verify the runtime will execute the included Python script locally and will not upload text to external services; and (4) optionally run the script in a sandbox or inspect it line-by-line to ensure no unexpected behavior.Like a lobster shell, security has layers — review code before you run it.
latestvk97bzzgh9a0bb2hgmg019yyxah84rvst
License
MIT-0
Free to use, modify, and redistribute. No attribution required.