agent-skills
Official Agent skills of Oxylabs products
No outside reports on file
Use this only if you trust the Oxylabs service, carefully control what data the agent can access, and never expose API credentials in logs or shared environments.
Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (oxylabs/agent-skills)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/oxylabs/agent-skills ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-23.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Agent Skills
This is a collection of AI agent skills for Oxylabs products, likely enabling automated tasks like web scraping, data extraction, or API interactions. The specific capabilities depend on which skills are included in the repository.
Who it’s for
Developers building AI agents that need to integrate with Oxylabs services (a web scraping and proxy platform). Teams automating data collection or web intelligence workflows.
Alternatives
- Apify SDK: Open-source web scraping and automation framework with built-in safeguards.
- Puppeteer: Headless browser library for controlled web automation.
- Beautiful Soup / Scrapy: Python libraries for parsing and scraping with explicit control.
- Custom API integrations: Direct use of target website APIs instead of scraping, where available.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README on GitHub at https://github.com/oxylabs/agent-skills (opens external site) for installation and configuration instructions specific to your use case.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 878
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Account access: The agent could use stored Oxylabs API credentials to make requests on your behalf, potentially incurring costs or accessing data you didn't intend to expose.
- Web scraping misuse: Skills might extract data from websites in ways that violate terms of service or laws like CFAA (Computer Fraud and Abuse Act) if not used carefully.
- Credential leakage: API keys or authentication tokens could be logged, cached, or accidentally sent to third parties if the agent isn't properly sandboxed.
- Deceptive prompts: An attacker's instructions could trick the agent into scraping sensitive sites, bypassing rate limits, or impersonating legitimate requests.
- Data in outputs: Extracted web content might contain personal information, copyrighted material, or malware that gets processed without filtering.
How to lower the risk
Least-privilege permissions
- Create dedicated Oxylabs API keys with minimal scopes for each agent.
- Restrict which websites or domains the agent is allowed to scrape.
Network isolation
- Run the agent in a container or sandbox to limit where it can send data.
- Use a firewall to block outbound traffic except to authorized endpoints.
Monitoring
- Log all API calls and extracted data for audit trails.
- Alert on unusual request volumes or targets that suggest misuse.
Red flags to watch for
- Sudden spikes in API usage or scraping of unexpected sites.
- Requests to extract personal data or bypass access controls.
- Agent trying to modify or delete data through the Oxylabs API.
Questions
How do I install Agent Skills?
Agent Skills does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/oxylabs/agent-skills.
Are there security reports about Agent Skills?
No reports found for this package in our research (last checked 2026-10-30). Agent Skills currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include account access, web scraping misuse, credential leakage.
Is Agent Skills actively maintained?
Agent Skills has 878 GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/oxylabs/agent-skills before pinning it in production.
What are alternatives to Agent Skills?
Notable alternatives to Agent Skills include Apify SDK (Open-source web scraping and automation framework with built-in review), Puppeteer (Headless browser library for controlled web automation), Beautiful Soup / Scrapy (Python libraries for parsing and scraping with explicit control), Custom API integrations (Direct use of target website APIs instead of scraping, where available). You can also compare Agent Skills side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Agent Skills? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/oxylabs-agent-skills)HTML embed:
<a href="https://agentarmorhq.com/skills/oxylabs-agent-skills"><img src="https://agentarmorhq.com/api/badge/oxylabs-agent-skills" alt="AgentArmorHQ Risk Grade for Agent Skills" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "oxylabs-agent-skills"Share with your security lead
Need sign-off to use agent-skills? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: agent-skills
- **Listing URL:** https://agentarmorhq.com/skills/oxylabs-agent-skills
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 878 GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (oxylabs/agent-skills)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/oxylabs/agent-skills
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- oxylabs
- Source code
- github.com/oxylabs/agent-skills
- Est. context load
- ~50 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 878 GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-23
Community
Discussions for Agent Skills
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude