plugin-security
OfficialThreat modeling for secure LLM extensions.
Software Engineering#security#heuristics#risk-assessment#threat-model#prompt-injection#hook-scripts#llm-extensions
AuthorEntelligentsia
Version1.0.0
Installs0
System Documentation
What problem does it solve?
LLM extensions occupy a privileged position and can be hijacked via prompt injection, hook scripts, or overly broad permissions, risking model behavior and user data.
Core Features & Use Cases
- Threat modeling framework for LLM extensions.
- Attack taxonomy covering prompt injection, host vs mind attacks, and data exfiltration.
- Practical heuristics and guardrails to assess risk before enabling any extension.
Quick Start
Review the LLM extension for prompt injection vulnerabilities and security risks before enabling any plugin.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: plugin-security Download link: https://github.com/Entelligentsia/skillforge/archive/main.zip#plugin-security Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.