Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Search Agent Skill
v1.0.0AI-powered search agent that performs intelligent web searches, aggregates results, and provides summarized answers with source citations. Use when: user nee...
⭐ 0· 56·0 current·0 all-time
bybittao@hgta23
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill's name/description (web search, summarization) aligns with the code and README: axios/cheerio are used to fetch and parse web pages and the module exposes search, quickSearch, factCheck, etc. Requiring a search API key and AI model for summarization is coherent with the stated purpose. However the registry metadata lists no required environment variables/credentials even though both SKILL.md and index.js reference SEARCH_API_KEY and AI_MODEL — a provenance/metadata inconsistency.
Instruction Scope
The SKILL.md instructions and the code focus on web search, content fetching, analysis, and formatting. The runtime instructions do not ask the agent to read unrelated local files or other credentials. The code fetches arbitrary URLs returned by search results (normal for a search tool), which means it will make outbound network requests and retrieve remote content.
Install Mechanism
No install spec is provided (instruction-only at registry level), which is low-risk for installation. The package includes code files and a package.json with dependencies (axios, cheerio) so the skill can be executed if installed via npm; there is no download-from-arbitrary-URL or extract step. Still, the registry/source is listed as 'unknown' while package.json points to a GitHub repo — source provenance should be confirmed before installing.
Credentials
The SKILL.md and index.js both reference environment variables (SEARCH_API_KEY, AI_MODEL, SEARCH_MAX_RESULTS, SEARCH_TIMEOUT, SEARCH_LANGUAGE). The registry metadata, however, declares no required env vars or primary credential. SEARCH_API_KEY (and potentially an AI_MODEL credential) is reasonable for this skill, but the failure to declare required credentials in the registry is a mismatch that could hide needed secrets. No unrelated credentials are requested.
Persistence & Privilege
The skill is not always-enabled and does not request elevated system persistence. It does not modify other skills or claim to write system-wide configuration. It will make outbound HTTP requests when invoked, which is expected for a search agent.
What to consider before installing
This skill appears to implement a legitimate web-search and summarization tool, but there are a few things to check before installing or using it:
- Confirm required credentials: the SKILL.md and index.js reference SEARCH_API_KEY and AI_MODEL, but the registry metadata declares none. You should assume an API key is needed; ask the publisher or check the upstream repository for which search service and key format are required.
- Verify source provenance: registry 'Source' is unknown while package.json points to github.com/clawhub/search-agent. Inspect that repository (or the uploaded files) to ensure it matches and is maintained by a trustworthy owner.
- Network behavior: the skill will fetch arbitrary webpages and call search APIs. Do not run it in an environment containing sensitive internal-only URLs you don't want exposed. Avoid giving it private or sensitive queries unless you control the search target and understand where requests go.
- Review dependencies & run audits: the package uses axios and cheerio (common), but run a dependency audit and optionally sandbox execution before granting it access to production systems.
- Ask for clarification: request that the publisher update the registry metadata to list SEARCH_API_KEY (and any other required env vars) and provide the concrete search API endpoints used (performSearch currently contains placeholder endpoints).
If the publisher confirms the above and provides a verifiable source repo/release, and you only provide the minimal API key with rate/permission controls, the inconsistencies would be explainable and the risk lowered.index.js:14
Environment variable access combined with network send.
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.
latestvk970qpnbg80752nggfq652mvkd84fm52
License
MIT-0
Free to use, modify, and redistribute. No attribution required.