← Back to Skills Marketplace
Parallel
by
Matt Van Horn
· GitHub ↗
· v1.2.1
2479
Downloads
3
Stars
10
Active Installs
11
Versions
Install in OpenClaw
/install parallel
Description
High-accuracy web search and research via Parallel.ai API. Optimized for AI agents with rich excerpts and citations. Supports agentic mode for token-efficien...
Usage Guidance
This skill appears to implement a legitimate Parallel.ai client, but there are a few red flags to review before installing:
- Inspect and remove the hard-coded API key in scripts/search.py. A hard-coded fallback means the skill may run using a credential you don't control; this can incur costs or leak usage to someone else. Replace it with strict failure when PARALLEL_API_KEY is missing or document an explicit demo key policy.
- Be aware of optional env vars not declared in the registry (BROWSERUSE_API_KEY, PARALLEL_MAX_WAIT). If you provide BROWSERUSE_API_KEY, the skill will forward it to an external MCP endpoint (browser-use.com) for authenticated browsing — that enables access to gated pages but also means sensitive page contents or credentials may be shared with that third party.
- Monitor webhooks and callbacks: monitor.create accepts a webhook URL that the Parallel service will call. Do not configure untrusted webhook URLs, since monitors may send content or alerts to those endpoints.
- Verify the pip package 'parallel-web' and the upstream Parallel.ai service before supplying your API key. Check account usage/quotas after first use.
- If you install: (1) remove or rotate any embedded keys, (2) run scripts in an isolated environment, and (3) prefer providing your own PARALLEL_API_KEY and avoid supplying optional third-party browsing keys or webhooks unless you trust those endpoints.
Given these inconsistencies and the embedded key, I recommend manual code review and remediation before enabling this skill for production use.
Capability Analysis
Type: OpenClaw Skill
Name: parallel
Version: 1.2.1
The skill bundle provides a functional interface for the Parallel.ai API but contains a hardcoded API key in `scripts/search.py`, which is a significant security vulnerability and credential leak. Additionally, `scripts/task.py` includes support for authenticated web browsing via a third-party service (browser-use.com), a high-privilege capability that increases the potential impact of misuse, although it is documented as a feature for deep research.
Capability Assessment
Purpose & Capability
Name/description match the files and runtime instructions: the scripts call Parallel.ai search, extract, findall, monitor, task, and task-run endpoints. Required PARALLEL_API_KEY is appropriate for this purpose.
Instruction Scope
Most instructions stay within the declared purpose (calls to Parallel.ai). However the skill accepts webhook URLs (monitor.create) and allows passing 'mcp_servers' for authenticated browsing (task.py), which cause data or credentials to be sent to third parties. search.py falls back to a hard-coded API key if PARALLEL_API_KEY is not set (inconsistent with other scripts that exit), which means the skill can operate under an embedded credential you did not provide.
Install Mechanism
This is instruction-only (no install spec that downloads arbitrary archives). It uses Python scripts and recommends 'pip install parallel-web' which is a normal package install; no unusual installers or remote extracts are present.
Credentials
Declared primaryEnv is only PARALLEL_API_KEY which is appropriate. But the code optionally uses other env vars not declared in metadata (BROWSERUSE_API_KEY for authenticated browsing, PARALLEL_MAX_WAIT) and search.py contains a hard-coded fallback API key string. Requiring or using extra credentials without declaring them and embedding an API key are disproportionate and risky.
Persistence & Privilege
The skill does not request always:true, does not modify other skills, and contains no code that persists itself into global agent config. Autonomous invocation is allowed (default) but not combined with other high privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install parallel - After installation, invoke the skill by name or use
/parallel - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.1
Fix display name (remove Clawdbot prefix)
v1.2.0
Rebrand: clawdbot → openclaw in metadata key and prose references.
v1.1.0
Republish after ClawHavoc moderation sweep. Updated descriptions, Grok-4/API 2026 notes, author/license/repository metadata.
v1.0.7
Version 1.0.7 (no file changes detected)
- No changes were made in this release; SKILL.md remains unchanged.
- No updates to functionality, documentation, or dependencies.
v1.0.6
- Updated requirements in metadata: now lists `curl` and `jq` as required binaries, and removes `BROWSERUSE_API_KEY` as a required environment variable by default.
- Clarified that `BROWSERUSE_API_KEY` is only needed for authenticated sources and is optional for basic usage.
- Minor improvements to documentation for setup and environment variable configuration.
- No changes to core workflow or usage.
v1.0.5
- Added explicit setup instructions with required Python packages (`parallel-sdk`, `requests`) and environment variable setup.
- Clarified which APIs and scripts use which Python packages.
- Strengthened security and permissions section to specify allowed endpoints and clarify what is not accessed.
- Updated instructions and formatting for clarity and quick start.
- Removed benchmark comparisons and language claiming outperformance of other products.
v1.0.4
Declare BROWSERUSE_API_KEY in requires.env to resolve undeclared credential flag
v1.0.3
Fix metadata key: use clawdbot namespace for registry recognition
v1.0.2
Fix security scan: add openclaw metadata, declare PARALLEL_API_KEY, remove hardcoded key, add Security section
v1.0.1
Updated description - removed competitor callouts
v1.0.0
Initial release: High-accuracy web search via Parallel.ai API with Search, Extract, and Task APIs
Metadata
Frequently Asked Questions
What is Parallel?
High-accuracy web search and research via Parallel.ai API. Optimized for AI agents with rich excerpts and citations. Supports agentic mode for token-efficien... It is an AI Agent Skill for Claude Code / OpenClaw, with 2479 downloads so far.
How do I install Parallel?
Run "/install parallel" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Parallel free?
Yes, Parallel is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Parallel support?
Parallel is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Parallel?
It is built and maintained by Matt Van Horn (@mvanhorn); the current version is v1.2.1.
More Skills