Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Keyapi Google Search
v1.0.0Perform Google web and image searches — retrieve ranked web results with titles, snippets, and URLs, or search for images with country and language targeting...
⭐ 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
medium confidencePurpose & Capability
The skill name/description (Google web/image search) align with the code and declared dependency (@modelcontextprotocol/sdk) that call a KeyAPI MCP server. Minor inconsistency: the run.js help defaults the platform to 'tiktok' while the SKILL.md focuses on the 'google' platform — this is likely a harmless default mismatch but worth noting.
Instruction Scope
SKILL.md and scripts instruct the user to run npm install and node scripts/run.js; the script reads/writes a .env file in the skill directory (can save your KEYAPI_TOKEN), creates a .keyapi-cache directory, and can write output files. These behaviors are within the expected scope for a client tool, but the token persistence and local caching are operational side-effects the user should expect.
Install Mechanism
No automated install spec is included; the package uses a single npm dependency (@modelcontextprotocol/sdk) declared in package.json. Requiring npm install is proportionate for a Node-based client. This is a standard, moderate-risk install model (npm registry dependency).
Credentials
Only KEYAPI_TOKEN (primaryEnv) and an optional KEYAPI_SERVER_URL are referenced. These match the stated purpose. No unrelated credentials or system-wide secrets are requested.
Persistence & Privilege
The skill does not request 'always: true' and cannot autonomously gain extra privileges beyond running when invoked. It does persist the token to a local .env and writes cache/output files in the skill directory — normal for a CLI client but something to be aware of.
Assessment
This skill appears to be what it says: a KeyAPI-based Google web/image search CLI. Before installing or running it: 1) Verify you trust the KeyAPI service (https://keyapi.ai) and the repository owner; 2) Be aware the script will save your KEYAPI_TOKEN into a .env file in the skill directory if you provide it interactively — run it from a directory where you’re comfortable storing that token or manually set the environment variable instead; 3) The tool writes a local cache (.keyapi-cache) and can write output files — check/clean those if needed; 4) Review or audit the included scripts (scripts/run.js) yourself if you have concerns (the code is present and readable); 5) Confirm the MCP server URL is correct before use (the script accepts KEYAPI_SERVER_URL override — don’t point it at untrusted endpoints, as that would send your token elsewhere). If you need higher assurance, verify the package maintainer and upstream repository and/or run the code in an isolated environment first.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.
latestvk979jbk18wdf1j25byd4jdy2bx8436ff
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🔍 Clawdis
Binsnode
EnvKEYAPI_TOKEN
Primary envKEYAPI_TOKEN