Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Web Claude
v1.0.0Unified web search skill. Fallback order — web_search(Brave) → duckduckgo → claude.ai. Auto-cache search results (saved to memory/research/)
⭐ 0· 1.6k·15 current·17 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The name/description (unified web search with Brave → DuckDuckGo → claude.ai) matches the SKILL.md behavior. However, the SKILL.md explicitly says a Brave API key is required and the claude.ai browser/login is required, yet the registry metadata lists no required env vars or primary credential. That discrepancy (claimed requirements not declared) is an incoherence.
Instruction Scope
Instructions are explicit about three-tier search and browser automation against claude.ai (navigate, type, press Enter, wait, snapshot). They also instruct automatic caching of every search result to memory/research/. These behaviors are within the stated search purpose, but the automatic persistent storage of search queries/results can leak sensitive queries and is not surfaced in the skill metadata or permission list.
Install Mechanism
This is instruction-only with no install spec or downloadable artifacts, so there's no installer risk. However, instructions assume third-party runtime components (Python and the duckduckgo_search library, and OpenClaw browser on port 18800) that are not declared as requirements.
Credentials
The SKILL.md refers to a Brave API key and to interacting with claude.ai (implying an authenticated session), but the skill metadata declares no required env vars/credentials. It also assumes access to a local memory path (memory/research/) where it will write cached results. Missing declarations of these credentials/dependencies is disproportionate and risky—users won't be informed about credential needs or persistent storage.
Persistence & Privilege
always:false and standard autonomous invocation behavior are fine. The more relevant persistence risk is that the skill will auto-create and write files into memory/research/ for every query. That is normal for a cache but is not declared in the metadata and can persist sensitive queries/results.
What to consider before installing
This skill mostly does what it says (three-tier web search plus caching), but there are important omissions and privacy concerns you should resolve before installing:
- Ask the author to explicitly declare required credentials and dependencies in the registry metadata: Brave API key (or how web_search obtains it), any duckduckgo_search Python package requirement, and that a logged-in claude.ai/OpenClaw browser is required.
- Understand and control local caching: the skill will auto-create memory/research/ and write every query and results there. If you may query sensitive topics, turn off caching or inspect/clean that folder regularly.
- Confirm runtime assumptions: the SKILL.md assumes Python and the duckduckgo_search package and an OpenClaw browser listening on port 18800. If you don't want those present, do not enable the skill.
- Rate-limit and automation detection: the skill instructs automated queries against claude.ai and warns about automation detection; use cautiously and prefer DuckDuckGo or Brave where possible.
- If you cannot verify the author or prefer tighter control, run the skill in a sandboxed agent with no access to sensitive credentials or restrict the skill's ability to write persistent storage.
If the author updates the metadata to declare required env vars (Brave key, any claude.ai token usage) and the dependency list (duckduckgo_search, Python), and documents the caching behavior and opt-out, this assessment could move to benign.Like a lobster shell, security has layers — review code before you run it.
latestvk9784m50was1djhxxpz5r2bmf1816ths
License
MIT-0
Free to use, modify, and redistribute. No attribution required.