← Browse
skill-security-scan
Zavelinski ★ 0
This skill statically vets untrusted third-party skills before installation by scanning the SKILL.md file, hooks, and settings.json for instruction injection, data exfiltration, dangerous commands, obfuscation, and other security risks, returning an ALLOW/REVIEW/BLOCK verdict with specific remediation advice. It ships an install-guard hook that automatically runs this scan whenever you attempt to install a skill or plugin in Claude Code.
Install
> /plugin marketplace add Zavelinski/claude-code-skill-security-scan
> /plugin install skill-security-scan
Source: https://github.com/Zavelinski/claude-code-skill-security-scan
What it's made of
1 skill · 1 hook
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 1 · UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
node- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (Zavelinski).