prompt-injection-scanner
CommunityAudit agent prompts for prompt hijacking risks.
Software Engineering#security#audit#risk-assessment#mitigation#prompt-injection#agent-prompts#instruction-hijacking
Authorjorgealves
Version1.0.0
Installs0
System Documentation
What problem does it solve?
The prompt-injection-scanner audits agent skill instructions and system prompts for vulnerabilities to prompt hijacking and indirect injection. Use when designing new agent skills or before deploying agents to public environments where users provide untrusted input.
Core Features & Use Cases
- Identifies weak points where malicious users could hijack agent behavior by inserting conflicting instructions into input fields.
- Provides timely guidance for secure skill design, pre-deployment review, and ongoing security auditing.
- Works with existing SKILL.md to surface potential injection vectors and recommended mitigations.
Quick Start
Run the scanner against your skill's SKILL.md to generate a risk report and mitigation recommendations.
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: prompt-injection-scanner Download link: https://github.com/jorgealves/agent_skills/archive/main.zip#prompt-injection-scanner 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 223,000+ vetted skills library on demand.