ask-threats
CommunityThreat analysis for AI agents using ASK.
Software Engineering#defense-in-depth#mcp#security-framework#ai-agents#attack-surface#threat-analysis#xpia
Authorgeoffbelknap
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill provides a structured, framework-backed approach to identifying and analyzing threats to AI agent systems using the ASK threat model, enabling teams to map risks, assess kill chains, and design defenses.
Core Features & Use Cases
- Threat categorization and risk assessment for traditional, novel, and hybrid threats to agents.
- Kill-chain posture evaluation across injection, propagation, execution, and exfiltration stages with recommended mitigations.
- Defensive architecture guidance for enforcing constraints, mediation, and gateway-level protections in MCP and delegation ecosystems.
Quick Start
Review your current agent threat model using the ASK framework and run an initial XPIA-focused risk inventory.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 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: ask-threats Download link: https://github.com/geoffbelknap/geoffs-plugins/archive/main.zip#ask-threats 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.