Enforcement defenses against prompt injection like CaMeL, Progent, IPIGuard and DRIFT share a design: take the security decision out of the model's context and give it to code. But the artifact that the code enforces — a program, a privilege policy, a dependency graph or a constraint list — is still written by the agent's own model. A paper posted to arXiv (2611.17115) by Zimo Xu, Wenzhuo Liu and Hideki Nakayama asks a blunt question: can small language models write these artifacts at all?
The setup
The testbed is AgentDojo v1.2.2 with its four suites (Workspace, Slack, Banking, Travel): 97 user tasks and 949 task-injection pairs, with attack success measured on the 929 pairs whose injection goal needs a tool call. Fifteen open-weight models: Qwen3-1.7B/-4B/-8B, Qwen3.5-4B/-9B, Llama-3.1-8B-Instruct, Gemma-4-E2B/-E4B/-12B, Granite-4.2-8B, Ministral-3-8B and LFM2.5-2.6B among thirteen small models, plus two larger references, Qwen3-32B and the mixture-of-experts Qwen3.6-35B-A3B. The main attack is AgentDojo's important_instructions; robustness runs add tool_knowledge and two attacks written specifically against CapLite's design.
Artifacts that decide what is allowed fail open
Progent has the model write a privilege policy from the request and update it after each call. Those policies admit attacks on 14 of 15 models, 676 in total, with Qwen3-32B alone at 132 of 929. The same policies block 25-77% of the write calls the agent attempts under attack, and benign utility drops from 59.4% to 43.8%: one artifact, wrong in both directions. IPIGuard's dependency graphs are breached on 13 of 15 models (435 attacks), and DRIFT's trajectory checklists on 11 of 15 (214 attacks). DRIFT's four clean models complete only 4.7-9.5% of attacked tasks — their zero comes from inaction.
Artifacts that decide what runs fail closed
CaMeL goes the other way: its interpreter enforces data-flow policies on whatever program the model writes, and security holds — 20 successful attacks in 13,935 episodes, 17 of them on LFM2.5-2.6B. The price: on 8 of the 15 models the final program is unrunnable in more than 15% of episodes, reaching 68% on Granite-4.2-8B, where the model returns no code at all. Format, syntax and interpreter errors survive ten repair rounds, the bill reaches 94k tokens per episode, and benign utility falls to 24.9%.
Bigger is not safer
Moving up the Qwen3 family from 1.7B to 32B raises the Progent attack success rate from 3.0% to 14.2%; on Gemma-4 it goes from 0% to 12.7%. Larger models are easier to inject, and the artifacts they write do not absorb the extra risk. Across all 15 models, no artifact failure rate shows a significant trend with capability (correlation magnitude at most 0.33, p above 0.2).
CapLite: the model proposes, code authorizes
CapLite's answer is to never let the model decide what is authorized. The policy is derived from the tool schemas by fixed rules, and the allowed values are exactly what the user's request states. A Planner that sees only the request commits the write calls before any tool result is read; a Mediator admits a write only when every authority argument — recipient, amount, object identifier, URL — equals a value stated in the request. No attack succeeds in any of the 13,935 attacked episodes, including the read exfiltration attack built to defeat it (0/168) and the descriptor collision attack (0/104). Utility under attack is comparable to CaMeL's (29.0% vs 27.2%) at 17.1k tokens per episode — 18% of CaMeL's 93.7k and below the undefended agent's 28.0k — with 1.69 utility per thousand tokens against 1.24 for DRIFT and 0.29 for CaMeL.
The bill the authors admit
Everything comes from one benchmark, AgentDojo's four suites. Utility under attack is 21 points below the undefended agent's (29.0% vs 50.2%): in 43% of CapLite's benign failures the committed plan misses a write the task needs, and in 38% every committed write runs but the task still fails — a plan without code cannot loop or branch. On Gemma-4-E4B and -12B utility is significantly below CaMeL's (those two write CaMeL programs reliably, failing only 3-14% of the time). Authority values the user never stated require a confirmation round-trip.
The line worth remembering is not the 0/13,935 but the conclusion: small models cannot be trusted to write their own defenses — and they do not need to. Once authorization belongs to deterministic code, the question becomes: how many security decisions in your agent stack are still a model improvising?