ClawHub

duckduckgo-search-skills

v1.0.0

Search the web using DuckDuckGo. No API key required. Supports instant answers and HTML scraping modes. Privacy-focused search alternative.

⭐ 0· 188·0 current·0 all-time
bycscsxx@cscsxx606
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (DuckDuckGo search, no API key) match the included code and SKILL.md. The skill only requires python3 and uses DuckDuckGo instant JSON API and the DuckDuckGo HTML endpoint as described; no unexpected services, binaries, or credentials are requested.
ℹ
Instruction Scope
SKILL.md instructs the agent to call the provided Python script with flags for instant/html/search/result-count/summarize and shows example exec() commands. The instructions do not ask the agent to read local files, environment secrets, or unrelated system state. One noteworthy capability: the script supports fetching page content from search results (--fetch-content) and will make outbound HTTP requests to result URLs; this is coherent with the stated feature but increases network activity and could access internal URLs if the environment permits.
✓
Install Mechanism
No install spec; this is an instruction-only skill with a single Python script. Nothing is downloaded or extracted during install. Requiring python3 is proportional and expected.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths and the code does not reference secrets or other env vars. The lack of requested credentials is appropriate for a scraper/instant-answer search tool.
✓
Persistence & Privilege
always is false and the skill does not request permanent/global privileges or modify other skills. It can be invoked by the model (normal default) but has no elevated persistence requirements.
Assessment
This skill appears to be what it claims: a Python-based DuckDuckGo search helper that can use the instant JSON API or scrape HTML. Before installing, consider: (1) If you enable --fetch-content, the script will make outbound HTTP requests to pages in search results — in sensitive environments that could reach internal endpoints (SSRF-like concern). (2) The script recommends scraping (HTML mode); heavy or automated scraping may trigger rate limits or legal/ethical issues — follow rate-limiting guidance in SKILL.md. (3) For production-critical, high-volume use, prefer an official API (as the SKILL.md itself suggests). If you want extra assurance, review the remainder of the script (the truncated portion handles output and maybe content fetching) to confirm there are no unexpected external endpoints or hidden logging/transmission of results to third parties.

Like a lobster shell, security has layers — review code before you run it.

latestvk978jzpf0e0a3rcr0fsxhtzsc182stde

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

🦆 Clawdis
Binspython3

Comments