← Back to Skills Marketplace
779
Downloads
0
Stars
1
Active Installs
5
Versions
Install in OpenClaw
/install openclaw-search-tool
Description
Search the web using LLMs via OpenRouter. Use for current web data, API docs, market research, news, fact-checking, or any question that benefits from live i...
Usage Guidance
This skill appears to do what it says: run a CLI that queries OpenRouter and returns citation-backed answers. Before installing: (1) verify the origin of the research-tool binary (inspect the GitHub repo or crate) because the CLI will send your queries to OpenRouter; (2) treat OPENROUTER_API_KEY as a secret (it enables access and billing on your OpenRouter account); (3) avoid sending sensitive personal or proprietary data through the tool unless you trust OpenRouter's handling and your account settings; (4) follow the author's recommendation to run it in a sub-agent so your main session doesn't block; and (5) if you want stronger assurance, review the CLI source code or build from source rather than running a prebuilt binary.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-search-tool
Version: 0.1.5
The skill is classified as suspicious due to a clear instance of prompt injection against the OpenClaw agent within `SKILL.md`. The instruction "⚠️ Never set a timeout on exec when running research-tool." directly commands the agent on how to execute the skill, demonstrating a vulnerability where markdown instructions can influence the agent's operational parameters. While the intent here appears benign (to prevent premature termination of a long-running task), it highlights an attack surface for manipulating agent behavior. Additionally, the skill performs external network calls to openrouter.ai and requires an API key, which are high-risk capabilities, though justified by its stated purpose as a web research tool.
Capability Assessment
Purpose & Capability
Name/description (web research via OpenRouter) align with required items: the skill needs the research-tool CLI binary and an OPENROUTER_API_KEY. The README/metadata references a GitHub repo, which is consistent with a third-party CLI wrapper.
Instruction Scope
SKILL.md contains only instructions to run the research-tool CLI (sessions_spawn/exec) and how to set flags; it does not instruct reading unrelated local files or secrets. It does reference optional env vars (RESEARCH_EFFORT, RESEARCH_MODEL) that are not listed in requires.env — these are configuration knobs, not extra secrets. It also warns not to set exec timeout (operational guidance) which is unusual but not a security issue by itself.
Install Mechanism
The skill is instruction-only (no install spec). SKILL.md suggests installing via `cargo install openclaw-search-tool`, which is a reasonable, traceable install mechanism for a Rust-based CLI. The registry did not include an automated install step; that's low risk but means users should verify the binary source themselves before installing.
Credentials
Only OPENROUTER_API_KEY is required (declared as primary credential), which is proportional to a tool that talks to OpenRouter. The docs mention additional optional env vars (RESEARCH_MODEL, RESEARCH_EFFORT) not declared in requires.env — these are non-sensitive configuration items. Users should remember the API key grants access/billing on OpenRouter and therefore is sensitive.
Persistence & Privilege
The skill does not request always:true or any system-wide config paths and does not attempt to persist beyond normal CLI usage. disable-model-invocation is false (normal) — the skill can be invoked by the agent but has no elevated installation privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-search-tool - After installation, invoke the skill by name or use
/openclaw-search-tool - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.5
- Updated documentation to clarify recommended usage from OpenClaw agents, including examples for sub-agent and exec calls.
- Added a warning not to set a timeout when running via exec, and described using yieldMs for background polling instead.
- Adjusted estimated time ranges for effort levels to more realistic durations (in minutes).
- Renamed main heading to "OpenClaw Research Tool" for clarity.
v0.1.4
- Added recommendation to run research-tool in a sub-agent to keep main sessions responsive.
- Updated documentation in SKILL.md with example usage of `sessions_spawn` for sub-agent execution.
- No changes to code or functionality; documentation improvement only.
v0.1.3
- The default value for the `--timeout` flag was removed; there is now no timeout by default.
- Documentation for the `--timeout` flag updated to reflect its new (optional) behavior. Queries now run until completion unless a specific timeout is set.
v0.1.1
- Added expected response time guidance for queries, noting that even low-effort mode may take a minute or more; high/xhigh effort can take 10+ minutes.
- Clarified that this slow timing is normal and due to live web search and synthesis.
- Added "homepage" field to metadata for improved discoverability.
- No functional command or API changes.
v0.1.0
- Initial release of the research-tool for web search via OpenRouter.
- Supports natural language questions with cited, up-to-date answers using LLMs (defaults to GPT-5.2 with web access).
- Multiple research effort levels (`low`, `medium`, `high`, `xhigh`) for controlling analysis depth and speed.
- Flexible model selection (any OpenRouter model, with optional `:online` for live web search).
- Advanced options including system prompt override, stdin input, max tokens, and timeouts.
- Clear output separation: results to stdout, progress and token usage to stderr.
- Useful tips, status indicators, and cost transparency included.
Metadata
Frequently Asked Questions
What is Openclaw Research Tool?
Search the web using LLMs via OpenRouter. Use for current web data, API docs, market research, news, fact-checking, or any question that benefits from live i... It is an AI Agent Skill for Claude Code / OpenClaw, with 779 downloads so far.
How do I install Openclaw Research Tool?
Run "/install openclaw-search-tool" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Openclaw Research Tool free?
Yes, Openclaw Research Tool is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Openclaw Research Tool support?
Openclaw Research Tool is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Openclaw Research Tool?
It is built and maintained by aaronn (@aaronn); the current version is v0.1.5.
More Skills