Google Search
v2.1.0Google web search via Gemini Search Grounding (primary) and Custom Search JSON API (fallback). Use for: (1) Synthesized answers with citations (grounded sear...
⭐ 3· 1.7k·2 current·2 all-time
byshaharsh@shaharsha
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description, required env vars (GOOGLE_API_KEY and optional GOOGLE_CSE_CX), and the declared dependency (google-genai) align with a skill that performs Gemini-grounded search and falls back to Custom Search. No unrelated credentials or tools are requested.
Instruction Scope
SKILL.md and the Python code instruct the agent to call Gemini via google-genai and the Google Custom Search API. Runtime actions are limited to network calls to Google APIs and local formatting; there are no instructions to read unrelated files, harvest other environment variables, or send data to non-Google endpoints.
Install Mechanism
Installer is a simple install.sh that runs pip install google-genai and a smoke test. This is a moderate-risk but expected install method (PyPI package). The script uses --break-system-packages as a first attempt (falls back), which can affect system-managed Python on some systems — a minor operational concern. There are no downloads from personal servers or URL shorteners, and no archives extracted from arbitrary hosts. Note: registry summary indicated 'no install spec' but the package includes an install.sh and an install hint in SKILL.md metadata — minor metadata inconsistency.
Credentials
Only GOOGLE_API_KEY is required as the primary credential; GOOGLE_CSE_CX and locale vars are optional and justified by raw/image modes. No unrelated secrets are requested.
Persistence & Privilege
The skill does not request always:true, does not modify other skills, and does not persist elevated system-wide privileges. It runs on-demand and via normal autonomous invocation behavior.
Assessment
This skill appears coherent and implements Google Gemini grounding plus Custom Search as described. Before installing: (1) ensure you supply a Google API key with only the necessary APIs enabled (Gemini + Custom Search) and restrict its allowed IPs/referrers and billing limits where possible; (2) be aware pip will install the google-genai package from PyPI — verify the package/version you install and consider installing in a virtualenv or isolated environment; (3) the installer runs a smoke test that executes the skill script (which will make network calls), so run install in a controlled environment if you are cautious; (4) if you will use raw/image modes, supply your own GOOGLE_CSE_CX (the skill will not embed any CSE IDs); (5) monitor quota and billing for API usage. If you want higher assurance, review the full python file (included) or pin the google-genai version before installing.Like a lobster shell, security has layers — review code before you run it.
latestvk977hjdb8etx27c7p16ga5hjcd814m1c
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🔍 Clawdis
EnvGOOGLE_API_KEY
Primary envGOOGLE_API_KEY
