Skip to content
Agentmart
Submit a tool

SkillsSafe Security Scanner

AI skill security scanner.

Connector by skillssafe.comOfficial · Domain verified by the MCP Registry

IndexedMITLocal (stdio)Remote (SSE)
Write a review

Install

Works with Claude Code, VS Code, Codex, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/skillssafe-com-scanner

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://mcp.skillssafe.com/sse Remote (SSE)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

AI skill security scanner. Detects prompt injection, credential theft, ClawHavoc. Free, no signup.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
2 read · 0 write · 0 deleteRead-only
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Tools by what they do 2

Read from the source code; the running server may list different tools.

Read 2 · Look things up without changing anything.

  • get_report
  • scan_skill

Network hosts it talks to 1

  • mcp.skillssafe.com · found in remote endpoint, install command

Tools (2)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • get_reportread-only

    Retrieve a previously generated scan report by scan_id. Returns a link to the full report page at skillssafe.com.

  • scan_skillread-only

    Scan an AI agent skill file (SKILL.md, MCP tool config, or system_prompt) for security threats before installation. Detects credential theft, data exfiltration, prompt injection, hidden zero-width characters, shell injection, reverse shells, memory poisoning, scope creep, and ClawHavoc malware indicators. Returns INSTALL/REVIEW/BLOCK decision with risk score 0–100. Free, no API key required. Supports OpenClaw, Claude Code, Cursor, and Codex skills.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Mar 13, 2026 (7 months ago)
Last release
Mar 12, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
com.skillssafe/scanner
Version
1.1.0
Auth
Auth not stated
Packages
npm skillssafe-mcp
License
MIT
Repository
github.com/GUCCI-atlasv/Skillssafe.com
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

SkillsSafe Security Scanner MCP server. Agent Mart. https://agentmart.dev/connectors/skillssafe-com-scanner (last updated 2026-10-24)