1. Conduid
  2. Files
  3. Agent Skill Scan Action
MCP server · Files

Agent Skill Scan Action

by · github.com/rexcoleman/agent-skill-scan-action

GitHub Action: Scan agent skill files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition risks.

Unclaimed last commit 6 months ago agent-securitygithub-actionllm-securitymcpprompt-injectionsecurity
InstallView source
34Low

Scored a month ago · breakdown

About Agent Skill Scan Action

Agent Skill Scan Action is an MCP server published by rexcoleman in the Files category: gitHub Action: Scan agent skill files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition risks.

The repository has 1 stars and 0 forks, with the last commit 6 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/rexcoleman/agent-skill-scan-action

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Agent Skill Scan Action

Powered by Claude · Grounded in docs

I know everything about Agent Skill Scan Action. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v1.0.0v1.0.0 — Agent Skill Scanner · 31 Mar 2026Scan agent skill files for security vulnerabilities in your CI pipeline. What's included 22 detection rules across 5 categories (prompt injection, capability escalation, data exfiltration, encoded payloads, composition risks) Composite…
Questions

About Agent Skill Scan Action

How do I install Agent Skill Scan Action?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Agent Skill Scan Action safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Agent Skill Scan Action still maintained?

The last commit was 6 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.