📦 Parallel 1.0.1 — 技能工具
v1.0.0High-accuracy web search and research via Parallel.ai API. 为 AI 智能体优化 with rich excerpts and citations.
1· 1.5k·0 当前·0 累计
by 安全扫描
OpenClaw
可疑
high confidenceThe skill largely matches its stated purpose (wrapping Parallel.ai search) but contains undeclared dependencies and a hardcoded API key fallback — mismatches that create risk and merit caution.
评估建议
This skill appears to do what it says (wrap the Parallel.ai search API) but contains two practical inconsistencies you should care about: (1) both scripts provide a hardcoded API key fallback — treat that as suspicious (it could be a leaked or shared credential that enables tracking, billing, or unauthorized access). (2) The shell script uses curl and jq and the Python script requires the 'parallel' SDK, yet the registry declares no required binaries/env vars. Before installing: ask the author t...详细分析 ▾
ℹ 用途与能力
Name/description match the code: both scripts call Parallel.ai endpoints and the SKILL.md shows the Parallel SDK. However the manifest declares no required binaries or env vars while the shipped shell script requires curl and jq and the Python code requires the parallel SDK/pip package. That mismatch (manifest says 'none' but files clearly need these tools) is inconsistent.
ℹ 指令范围
SKILL.md stays within the stated scope (how to call the Parallel SDK and examples). The runtime scripts perform only search/research operations against api.parallel.ai. Nothing in SKILL.md instructs the agent to read unrelated system files. Still, the example uses {baseDir}/scripts/search.py and the shell script will call curl/jq — the instructions omit those runtime details and the presence of a baked-in API key is not documented in the SKILL.md.
✓ 安装机制
There is no install spec (instruction-only), which minimizes disk-write risk. SKILL.md does ask to pip install the Parallel SDK (parallel-web); that is a reasonable, proportional dependency for this skill.
⚠ 凭证需求
The code uses an environment variable PARALLEL_API_KEY but the registry metadata lists no required env vars. Worse, both scripts include a hardcoded API key fallback ("y2s_m4er5i6-5qCikOLUtmnkvOYRU24eDphq_jg1"). Embedding a live-looking API key in code is a red flag: it may be a leaked/privileged credential (billing/tracking risk), or it may allow the skill author to monitor or bill API usage. The skill asks network access to an external API (expected for a search skill) but does not declare or justify the embedded key.
✓ 持久化与权限
The skill does not request permanent presence (always:false) and does not modify other skills or system configs. It does allow autonomous invocation (platform default), which increases blast radius but is not itself unusual.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/1/26
Initial release of the parallel skill for high-accuracy web research. - Provides web search via the Parallel.ai API optimized for AI agents. - Delivers structured results with rich excerpts, citations, and API usage stats. - Supports deep research, fact-checking, and multi-hop reasoning tasks. - Includes setup instructions for Python SDK and command-line usage examples. - Reference links to official documentation and platform included.
● 无害
安装命令
点击复制官方npx clawhub@latest install parallel-1-0-1
镜像加速npx clawhub@latest install parallel-1-0-1 --registry https://cn.longxiaskill.com✓ 镜像可用
技能文档
High-accuracy web search API built for AI agents. Outperforms Perplexity/Exa on research benchmarks.
Setup
pip install parallel-web
API key is configured. Uses Python SDK.
from parallel import Parallel
client = Parallel(api_key="YOUR_KEY")
response = client.beta.search(
mode="one-shot",
max_results=10,
objective="your query"
)
Quick Usage
# Search with Python SDK python3 {baseDir}/scripts/search.py "Who is the CEO of Anthropic?" --max-results 5
# JSON output python3 {baseDir}/scripts/search.py "latest AI news" --json
Response Format
Returns structured results with:
search_id- unique search identifierresults[]- array of results with:
url - source URL
- title - page title
- excerpts[] - relevant text excerpts
- publish_date - when available
usage- API usage stats
When to Use
- Deep research requiring cross-referenced facts
- Company/person research with citations
- Fact-checking with evidence-based outputs
- Complex queries that need multi-hop reasoning
- Higher accuracy than traditional search for research tasks
API Reference
Docs: https://docs.parallel.ai Platform: https://platform.parallel.ai