prompt-injection-risk
CommunityConduct a thorough prompt-injection risk review for GenAI systems in financial services.
Authoranotb
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill helps financial institutions conduct a comprehensive review of the prompt-injection threat surface for GenAI systems, ensuring the identification and mitigation of potential risks.
Core Features & Use Cases
- Threat Surface Enumeration: Identifies all potential carriers of prompt-injection risks (system prompt, user input, retrieved content, tool output, agent memory, multi-agent message, multimodal input).
- Risk Assessment: Evaluates the trust posture and attack classes against each carrier, and the mitigations in place.
- Residual Risk Analysis: Determines the likelihood and impact of residual risks, and the recommended owner actions.
- Monitoring and Detection: Lists production signals and incident response procedures.
- Use Case: A bank is deploying a new GenAI system for customer support. Use this Skill to review the system's prompt-injection posture before deployment, ensuring all potential risks are identified and mitigated.
Quick Start
Use the prompt-injection-risk skill to review the GenAI system for the customer-support assistant, including its architecture, threat surface, and residual risks.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferencesassets
💻 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-risk Download link: https://github.com/anotb/second-line-financial-services/archive/main.zip#prompt-injection-risk 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 620,000+ vetted skills library on demand.