Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Keyapi Linkedin Company Analysis
v1.0.0Explore and analyze LinkedIn companies — retrieve company profiles, employee directories, published posts, job listings with rich filters, job counts, and in...
⭐ 0· 26·0 current·0 all-time
by@lycici
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill is an adapter for the KeyAPI MCP service and requires node and a KEYAPI_TOKEN — both are reasonable and expected for a CLI tool that calls an external API. The package.json and scripts implement an MCP client and caching layer consistent with the described LinkedIn company-analysis functionality.
Instruction Scope
Runtime instructions tell the agent/user to run node scripts/run.js and to npm install the SDK — consistent with the skill. Two noteworthy items: the runner's default platform is 'tiktok' while SKILL.md targets 'linkedin' (you must pass --platform linkedin or the platform default will be different), and the instructions and code explicitly persist the API token to a .env file and cache API responses locally (.keyapi-cache).
Install Mechanism
There is no opaque download/install URL; dependencies are installed via npm (declared dependency @modelcontextprotocol/sdk). This is a standard package-manager install and proportionate to the task. No remote archive extraction or unusual install hosts were used.
Credentials
Only KEYAPI_TOKEN is required (primary credential) which is appropriate. The code will also read/write a .env file in the skill directory and write cached API responses to .keyapi-cache and optionally output files — this is functional but means your token and API responses are stored on disk in the skill folder unless you avoid the interactive prompt or manage .env yourself.
Persistence & Privilege
The skill does not request system-wide privileges or set always:true. However, it writes files into the skill directory (.env and .keyapi-cache) and can persist credentials there; this is normal for a local CLI but worth considering if the skill directory is in a shared or committed repository.
Scan Findings in Context
[no_regex_findings] expected: Static pre-scan reported no injection signals or suspicious regex matches. The absence of findings is consistent with a small CLI wrapper that performs HTTP calls and local caching, but not proof of safety — the code does persist secrets and cache data locally.
Assessment
This skill appears to do what it says: it calls KeyAPI's MCP endpoints to fetch LinkedIn data. Before installing, consider: 1) Where will the KEYAPI_TOKEN live? The runner will prompt and (by default) save the token to a .env file in the skill directory — avoid storing secrets in repositories or shared folders. 2) The tool writes API responses to .keyapi-cache and any --output path you pass; if these responses contain sensitive info, secure or ignore that directory. 3) Always run npm install from a network you trust and review the @modelcontextprotocol/sdk package if you have concerns. 4) Note the minor runner mismatch: pass --platform linkedin when calling tools (the script defaults to 'tiktok' otherwise). If you want higher assurance, inspect the complete scripts/run.js in your environment and run the tool in an isolated container or ephemeral environment.scripts/run.js:52
Environment variable access combined with network send.
scripts/run.js:37
File read combined with network send (possible exfiltration).
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.Like a lobster shell, security has layers — review code before you run it.
latestvk9733c3araxgny3nt985j9dzdh8430xq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🏢 Clawdis
Binsnode
EnvKEYAPI_TOKEN
Primary envKEYAPI_TOKEN