Works with the AI tools you already use
AI Agent Threat Model — Prompt Injection & Tool Misuse
by monna
Map trust boundaries, trace injection-to-tool attack paths, and prioritize concrete controls before an AI agent ships.
Secure checkout via Stripe
See it in action
You say
Threat-model our support agent. It reads customer emails and RAG results, can search the knowledge base, send emails, and issue refunds up to $500 without human approval. We have not documented vector-store write validation or customer-level retrieval scoping.
Your agent does
VERDICT: NOT-DEPLOYABLE
CRITICAL — Combined tampering + elevation path Untrusted email content reaches the model context while the refund tool can act without human review.
Evidence: Stated Confidence: 88% — based mainly on stated autonomy and tool authority Priority control: require human confirmation for refunds, isolate untrusted content from instructions, and cap tool authority.
What you get
About this skill
What it does
An AI agent can turn untrusted text into a real action. This skill reconstructs the system as a data-flow diagram, applies STRIDE to every relevant element, and treats prompt injection plus high-impact tool access as one compound path instead of two disconnected checklist items.
What you get
- A deployment verdict and AI data-flow inventory.
- Trust boundaries and a STRIDE-per-element matrix.
- Evidence-tagged findings with confidence scores.
- A mitigation roadmap ordered by consequence.
- A deterministic coverage check for every applicable STRIDE category and the combined injection-to-tool path.
Worked path included
Send no architecture and the skill runs a labeled demonstration on its built-in customer-support agent. The package also includes a complete worked example and a universal prompt edition for capable chat models that do not load skills directly.
Known limitations
This is a design-stage threat model, not a penetration test or safety certification. It works from the architecture and permissions you describe, does not inspect a live system, and does not generate adversarial instruction payloads or working exploits. Classic web/API logic and cloud IAM require their own reviews.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Frequently Asked Questions
Popular in AI Agents & LLM Ops
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
agentic-workflow
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.

prompt-engineer
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
benchmarking-ai-agents-beyond-models
Published AI benchmarks measure brains in jars. They test models in isolation or within a single reference harness — and then attribute all performance to the model. This skill teaches you to decompose agent performance into its two actual components: model capability and harness multiplier. The result is evaluations that predict real-world behavior instead of benchmark theater.