Clawvicular
v1.0.0Daily looksmaxxing slang tip + Clavicular news. Extremely online Gen Z energy.
⭐ 0· 831·0 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 (daily looksmaxxing slang tip + Clavicular news) aligns with the provided references and runtime steps: pick a slang term from slang-dictionary.md, fetch recent web content about Clavicular, format two posts, and update local state and sources. No unrelated env vars, binaries, or install steps are requested.
Instruction Scope
SKILL.md instructs the agent to read/write files under its own baseDir (state/sent-terms.json and references/*.md) and to perform web searches for current content (Urban Dictionary, TikTok/X/Kick/etc.). Those actions are within the skill's described purpose. The only external network activity is web searching/fetching public URLs for news, which the skill explicitly requires. It does not instruct reading unrelated system files or environment variables.
Install Mechanism
This is an instruction-only skill with no install spec and no code files to download or run. That minimizes disk persistence and supply-chain risk.
Credentials
The skill requires no environment variables, credentials, or external service tokens. All requested file access is scoped to its own baseDir. The absence of extra secrets is proportionate to the claimed functionality.
Persistence & Privilege
always is false (not force-included). The skill writes/updates files only within its own baseDir (state and references), which is consistent with its stated need to track sent terms and an index of sources. It does not request system-wide configuration changes or other skills' credentials.
Assessment
This skill is internally coherent: it reads and updates files inside its own skill folder and performs web searches to build a daily slang tip + community news post. Things to consider before installing: (1) it will create and modify state/sources files in the skill directory—inspect those files for any content you don't want stored locally; (2) it performs web searches and will include/record public URLs (which may contain controversial or sensitive allegations about a real person), so review the references content to decide if you want that material archived; (3) the cron example can post into your channels — if you schedule it, ensure you configure the correct channel ID and use an isolated session if you want to limit blast radius; (4) because the agent can autonomously invoke skills by default, monitor automated runs initially. If you want stronger isolation, run the skill in an isolated session or review/modify the references/state files before use.Like a lobster shell, security has layers — review code before you run it.
latestvk97ebt4xv7v13gkcv37sk27chd80zzpf
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
💀 Clawdis
