Clawhub Publish Kmwrip1j
v0.4.0Analyze a user's MBTI from authorized OpenClaw memory, session history, and workspace notes. Use when the user asks for MBTI analysis, personality inference...
⭐ 0· 59·0 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
The name and description (MBTI analysis from OpenClaw memory, sessions, workspace notes) match the actual artifacts: SKILL.md describes discovery/authorization/ingest/infer/report pipeline and the repository includes Python scripts to discover sources, ingest content, build an evidence pool, infer MBTI, and render reports. Required binary is only python3, which is appropriate.
Instruction Scope
SKILL.md explicitly instructs discovery of candidate sources, asking the user to authorize specific categories, and then only ingesting approved sources. It references reading local OpenClaw paths (~/.openclaw/*) and workspace files (MEMORY.md, memory/*.md) which is necessary for the stated task. The doc also lists explicit exclusions (.env, credentials/*, identity/*, logs), and mandates the authorization step before reading content.
Install Mechanism
There is no install spec (instruction-only skill) and included code is run by python3. No remote downloads or package installers are declared, so nothing arbitrary is pulled from the network during install.
Credentials
The skill requests no environment variables or external credentials and only needs read access to local OpenClaw workspace and session files to perform its purpose. The access requested aligns with the goal of analyzing historical conversations and notes.
Persistence & Privilege
always is false and the skill does not claim to modify other skills or system-wide agent settings. Runtime behavior writes report artifacts into a local ./ .mbti-reports/<timestamp>/ directory (normal for report generation). Autonomous invocation is allowed by default but is not an unusual privilege here.
Assessment
This skill appears coherent and runs locally with python3. Before installing or running it: (1) review the scripts yourself (especially discover_sources.py and ingest_all_content.py) to confirm they only read files you authorize and do not call external endpoints; (2) follow the SKILL.md authorization step — explicitly approve which source categories the skill may read; (3) avoid granting access to highly sensitive files (credentials, identity, gateway logs) even if suggested defaults exclude them; (4) run the skill in an isolated environment or with limited filesystem permissions if you want extra assurance; and (5) if you need absolute assurance of no network exfiltration, grep the code for network calls (requests, urllib, sockets) and test in an offline environment first.Like a lobster shell, security has layers — review code before you run it.
latestvk971gzy10dtbtc7xmvezgmftcd848qmh
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧠 Clawdis
Binspython3
