claude-skills
Collection of Agent skills for enhanced AI workflows
No outside reports on file
Without clear documentation of what each skill does and what it can access, this project carries moderate risk of unintended data exposure or system changes, especially since it has very limited real-world usage and community review.
Based on public adoption and transparency signals as of Oct 29, 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
- CredentialsNo API token requiredLOW
- Package sourceGitHub (glebis/claude-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/glebis/claude-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 2026-10-29.
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 Claude Skills
Claude-skills is a collection of add-on abilities (called skills) designed to extend what Claude AI can do in automated workflows. It appears to provide extra functions that Claude can use to accomplish tasks, though specific skill details are not clearly documented in available sources.
Who it’s for
Developers building AI agents or automation systems who want to give Claude additional capabilities beyond its base features. Teams looking to customize Claude's behavior for specific workflows.
Alternatives
- OpenAI GPT actions: Official way to extend ChatGPT with custom API calls. - Anthropic's official tools/integrations: Claude's supported connectors and plugins. - LangChain tools: Open-source library for giving AI agents reusable capabilities. - Custom API wrappers: Build your own skill layer specific to your trusted APIs only.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README. The repository is available at https://github.com/glebis/claude-skills (opens external site), though installation steps are not confirmed from public documentation.
Why this grade
Signal-based grade (3/7 points): listed in several sources, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 403
- 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
- Undefined permissions: The skills can apparently execute actions, but it's unclear what systems, files, or APIs they can access or modify. - Hidden capabilities: Skills loaded from external sources could include undocumented features that perform unintended operations. - Data leakage: If skills process sensitive information (passwords, API keys, private data), they may store or transmit it without clear oversight. - Third-party risk: The project has minimal adoption (0 npm downloads weekly, 3 Hacker News points), suggesting limited security review by the community. - Prompt injection: Claude could be tricked into using skills in harmful ways if an attacker controls input data or system prompts.
How to lower the risk
Least-privilege permissions
- Only enable skills your workflow actually needs.
- Run Claude with minimal file system and network access.
Network isolation
- Restrict Claude's outbound connections to known safe APIs only.
- Monitor and log all network calls the skills make.
Monitoring
- Audit which skills are installed and what they claim to do.
- Log all actions Claude takes using these skills.
Red flags to watch for
- Skills that request broad file or network permissions without clear reason.
- Vague documentation about what a skill actually does.
- Skills that handle passwords, tokens, or sensitive data.
Questions
How do I install Claude Skills?
Claude Skills does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/glebis/claude-skills.
Are there security reports about Claude Skills?
No reports found for this package in our research (last checked 2026-10-30). Claude Skills currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include undefined permissions.
Is Claude Skills actively maintained?
Claude Skills has 403 GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/glebis/claude-skills before pinning it in production.
What are alternatives to Claude Skills?
Notable alternatives to Claude Skills include OpenAI GPT actions (Official way to extend ChatGPT with custom API calls. - **Anthropic's official tools/integrations**: Claude's supported connectors and plugins. - **LangChain tools**: Open-source library for giving AI agents reusable capabilities. - **Custom API wrappers**: Build your own skill layer specific to your trusted APIs only). You can also compare Claude Skills side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Claude 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/glebis-claude-skills)HTML embed:
<a href="https://agentarmorhq.com/skills/glebis-claude-skills"><img src="https://agentarmorhq.com/api/badge/glebis-claude-skills" alt="AgentArmorHQ Risk Grade for Claude Skills" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "glebis-claude-skills"Share with your security lead
Need sign-off to use claude-skills? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: claude-skills
- **Listing URL:** https://agentarmorhq.com/skills/glebis-claude-skills
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 403 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:** No API token required
- **Package source:** GitHub (glebis/claude-skills)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/glebis/claude-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 29, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- glebis
- Source code
- github.com/glebis/claude-skills
- Est. context load
- ~50 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 403 GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-29
Community
Discussions for Claude 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