L2.2.3 — Application, agent & supply-chain planes in depth¶
Type: Theory · Duration: ~5 min · Status: Mandatory Module: Module 2 — AI Security Foundations Framework tags: OWASP LLM02, LLM05, LLM08 · ATLAS AML.TA0011 (Impact), AML.T0010 (ML Supply Chain Compromise)
Learning objectives¶
- List four attack surfaces unique to the application plane, three unique to the agent layer, and three unique to the supply chain.
- Recognize that infrastructure-plane attacks are mostly classical infra security — and where the AI specifics are bolted on.
Core content¶
Application plane — four primary surfaces¶
- The user-input boundary. Where untrusted text first enters the system. Most prompt-injection defenses (input filters, length limits, schema-validated input) live here.
- Prompt template authoring. The static prompt scaffolding — system prompt, few-shot examples, persona definitions. Often the most leaked artifact in production. System-prompt extraction (OWASP LLM07) lives here.
- The output renderer. Whatever displays model output to the user — HTML renderer, markdown parser, voice synthesizer. Output handling vulnerabilities (XSS via LLM output, SSRF via auto-fetched URLs, SQL injection via formatted-string queries) live here. OWASP LLM02.
- The tool-call boundary (if agentic). Where model output triggers a tool invocation. Authorization decisions about which tools to expose, and with what arguments validation, live here.
Agent layer — three unique surfaces (subset of the application plane, important enough to call out)¶
-
Tool definitions. What tools is the agent allowed to call? Over-broad tool surfaces are the canonical excessive-agency vulnerability. A "send_email" tool that accepts any recipient is a different beast than one restricted to the user's own address.
-
Agent loop logic. Many agents have a plan-act-observe loop. An attacker who lands a single injection can plant goals that persist across loop iterations — plan-hijacking. Module 3 has a lab on this.
-
Inter-agent communication (multi-agent systems). When agent A's output becomes agent B's input, agent B treats it as authoritative — even though A may have been compromised by an injection three hops back.
Supply chain plane — three primary surfaces¶
-
Model weights. Any pre-trained or fine-tuned model you pull from a registry. Risk: weight files with malicious pickle payloads (Module 4 lab L4.8), backdoor triggers planted during training, model card lies about training data or evaluation results.
-
Datasets. Training data, fine-tune data, eval data downloaded from HuggingFace / Kaggle / other registries. Risk: poisoned examples, label flips, embedded triggers.
-
Libraries and frameworks. LangChain, the embedding-model library, the vector DB SDK, the agent framework, the inference runtime. Classical supply-chain risk plus AI-specific concerns (e.g., a vulnerable LangChain version that lets arbitrary code execute in a chain definition).
Infrastructure plane¶
Mostly classical infrasec — GPUs, containers, K8s, network, secret stores. The AI specifics are: - API keys for LLM providers are high-value targets (theft = unbounded compute spend). - GPU schedulers can be a side channel for model-extraction attacks against shared inference clusters. - Vector DBs are new infrastructure components with their own auth and isolation stories. Don't assume they have the maturity of Postgres.
The general rule: do classical infrasec first, then layer the AI specifics. If your infra plane has classical gaps, those will be exploited long before anyone bothers with AI-specific cleverness.
Real-world example¶
LangChain has shipped multiple CVEs (notably CVE-2023-29374 and successors) where chain-definition strings could trigger arbitrary code execution via insufficient sandboxing of expressions inside templates. This is a supply-chain attack: a defender using the library with default config inherits the vulnerability without any AI-specific mistake on their part. Module 4 covers SBOM and dependency review for the AI stack specifically.
Key terms¶
- Tool-call boundary — the API surface between the model's output and the agent's tool invocation.
- Plan-hijacking — agent-loop attack where an injected goal persists across iterations.
- AI-BOM — AI Bill of Materials; the inventory of artifacts and their provenance. Module 4.
References¶
- OWASP LLM Top 10 entries LLM02 (Insecure Output Handling), LLM05 (Supply Chain), LLM08 (Excessive Agency).
- LangChain CVE history — https://www.cve.org/CVERecord/SearchResults?query=langchain
- MITRE ATLAS AML.T0010 (ML Supply Chain Compromise) — https://atlas.mitre.org/techniques/AML.T0010
Quiz items¶
- Q: A defender restricts the agent's
send_emailtool to only allow the authenticated user's own address as recipient. Which OWASP entry is this defending against? A: LLM08 — Excessive Agency. - Q: Your model output renders into the user's browser as HTML. The model is tricked into emitting a
<script>tag. Which OWASP entry? A: LLM02 — Insecure Output Handling (output XSS). - Q: Why is the infrastructure plane "mostly classical" but not entirely? A: Classical infra controls apply, but AI-specific items (LLM API keys with unbounded compute spend, GPU side channels, immature vector-DB auth) need additional attention.
Video script (~620 words, ~4.5 min)¶
[SLIDE 1 — Title]
Application, agent, and supply-chain planes in depth. Plus a quick word on infrastructure. Five minutes.
[SLIDE 2 — Application plane: four surfaces]
Application plane — four surfaces. One: the user-input boundary, where untrusted text first enters the system. Most prompt-injection defenses live here — input filters, length limits, schema-validated input. Two: prompt template authoring. The static prompt scaffolding — system prompt, few-shot examples, persona definitions. Often the most leaked artifact in production. System-prompt extraction lives here.
Three: the output renderer. Whatever displays model output to the user — HTML renderer, markdown parser, voice synthesizer. Output-handling vulnerabilities live here. XSS via model output. SSRF via auto-fetched URLs. SQL injection via formatted-string queries. OWASP LLM02.
Four: the tool-call boundary, if the application is agentic. Where model output triggers a tool invocation. Authorization decisions about which tools to expose, and what arguments to validate, live here.
[SLIDE 3 — Agent layer: three unique surfaces]
Agent layer — three unique surfaces. Subset of the application plane but important enough to call out. One: tool definitions. What tools is the agent allowed to call? Over-broad tool surfaces are the canonical excessive-agency vulnerability. A send-email tool that accepts any recipient is a different beast than one restricted to the user's own address.
Two: agent loop logic. Many agents have a plan-act-observe loop. An attacker who lands a single injection can plant goals that persist across loop iterations — plan-hijacking. Module 3 has a lab on this.
Three: inter-agent communication, for multi-agent systems. When agent A's output becomes agent B's input, agent B treats it as authoritative — even though A may have been compromised by an injection three hops back.
[SLIDE 4 — Supply chain: three surfaces]
Supply chain plane — three surfaces. One: model weights. Any pre-trained or fine-tuned model you pull from a registry. Risk: weight files with malicious pickle payloads, backdoor triggers, model card lies. Two: datasets. Training data, fine-tune data, eval data downloaded from HuggingFace, Kaggle, others. Poisoned examples, label flips, embedded triggers. Three: libraries and frameworks. LangChain, embedding-model libraries, vector DB SDKs, agent frameworks, inference runtimes. Classical supply-chain risk plus AI-specific concerns.
[SLIDE 5 — LangChain CVE anchor]
One anchor. LangChain has shipped multiple CVEs where chain-definition strings could trigger arbitrary code execution via insufficient sandboxing of expressions inside templates. This is a supply-chain attack. A defender using the library with default config inherits the vulnerability without any AI-specific mistake on their part. Module 4 covers SBOM and dependency review for the AI stack.
[SLIDE 6 — Infrastructure plane]
Infrastructure plane. Mostly classical infrasec — GPUs, containers, Kubernetes, network, secret stores. The AI specifics: API keys for LLM providers are high-value targets, theft equals unbounded compute spend. GPU schedulers can be a side channel for model extraction against shared inference clusters. Vector DBs are new infrastructure with their own auth and isolation stories — don't assume they have the maturity of Postgres. General rule: do classical infrasec first, then layer AI specifics. If you have classical gaps, those will be exploited long before anyone bothers with AI-specific cleverness.
[SLIDE 7 — Up next]
Next three lessons we deep-dive on MITRE ATLAS. Tactics, techniques, case studies. See you there.
Slide outline¶
- Title — "Application, agent & supply-chain planes in depth".
- Application plane: four surfaces — quadrant with sample attack per surface.
- Agent layer: three surfaces — agent-loop architecture sketch with surfaces called out.
- Supply chain: three surfaces — supply-chain graph: registry → weights/datasets/libs → your system.
- LangChain CVE anchor — CVE history mini-timeline.
- Infrastructure plane — classical infra icons + AI-specific overlays.
- Up next — "L2.3.1 — What ATLAS is and how it relates to ATT&CK, ~4 min."
Production notes¶
- Recording: ~4.5 min. Cap 5.
- Slide 5 (CVE history) needs to be updated annually — flag in the production review SOP.