SBTI Test Now
v1.0.0Run the self-contained SBTI personality test when users ask for sbti 人格, sbti 人格测试, sbti test, sbti personality, sbti 中文测试, sbti 是什么, what is sbti, sbti mean...
⭐ 0· 71·0 current·0 all-time
by@fechin
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the included files (data/question-bank.json, scripts/run_sbti.py, scripts/sbti_engine.py). All required functionality (asking questions, scoring, producing a vector and matches) is implemented locally; nothing requested is disproportionate to running a self-contained personality test.
Instruction Scope
SKILL.md instructs the agent to run the bundled Python script or to follow the manual workflow using the bundled JSON. Instructions only reference local files and producing the test output; they do not direct reading of unrelated system files, exporting secrets, or calling unknown external endpoints. The SKILL.md does include an informational external URL (https://sbti.now/) but the runtime instructions do not require network access.
Install Mechanism
There is no install spec; the skill is instruction-plus-bundled-scripts only. All code is included in the skill bundle (no downloads, no external package installs), so there is no installer risk.
Credentials
The skill declares no required environment variables or credentials and the Python code only reads the bundled JSON and stdin/stdout. No unrelated credentials, config paths, or secrets are requested.
Persistence & Privilege
The skill is not always-enabled, does not request persistent system privileges, does not modify other skills' configurations, and does not attempt to write outside its bundle. Autonomous invocation is allowed by platform default but not combined with other red flags here.
Assessment
This skill is self-contained and appears safe to run: it uses local Python scripts and a bundled JSON question bank and asks no secrets. Before installing, confirm your host allows executing local Python files if you want the interactive runner (otherwise the manual workflow can be used). Be aware that answers you provide will be processed locally but may be logged by the host — if you are concerned about privacy, run the manual workflow or avoid sharing sensitive personal data. If you want extra assurance, inspect the bundled scripts (scripts/*.py) yourself; they are short and do not perform network I/O or read other system files.Like a lobster shell, security has layers — review code before you run it.
latestvk977kfx0c02smdhr4r473zntbd84jy1q
License
MIT-0
Free to use, modify, and redistribute. No attribution required.