One Polite Sentence Redirected a Small AI Classifier on 71% of Tested Tickets
Part 2 of 6. If a model sorts text that strangers write, anyone can append a sentence and steer it. I tested six such sentences on 500 tickets and four defences. A polite sentence asking for a different team worked on 71% of tickets. Telling the model its output must be a valid label did nothing, and wrapping the ticket in markers helped on exactly one kind of attack.
Bart Porcincula · Published
Finding
Appending one sentence to a support ticket moved a Qwen3.5-9B queue answer to the sentence's target on 71.2% of 500 tickets and the priority answer to "high" on 64-69% (baseline accuracy 32% and 40%); constraining the output to valid labels left the rate at 67.3% against 67.2%, and delimiters plus a data note cut one attack from 33.0% to 6.4% but did not move another (71.2% to 72.4%).
One-sentence injection into support-ticket triage, with four defences (Oct 2026)
Six appended sentences (three wording styles, two targets: send the ticket to a named team, and set priority to high) on 500 support tickets, run undefended and under three defences (constrain the output to valid labels, wrap the ticket in markers with a note that it is data, both). Four tickets at once, so each cell carries the roughly 21-in-500 noise floor measured in part 1. The sentences themselves are not published. Success is the share of tickets whose answer moved to the target.
| Measurement | Value | Note |
|---|---|---|
| Baseline accuracy, queue / priority | 32% / 40% | the model is already weak on these questions, so the attack starts from a low floor |
| Undefended: queue moved to target, best sentence | 356 of 500 (71.2%) | a polite, social-style sentence |
| Undefended: queue moved to target, direct command / authority-styled | 165 (33.0%) / 18 (3.6%) | the authority wording mostly failed on this target |
| Undefended: priority moved to high, three styles | 64.2% / 69.2% / 68.2% | mean 67.2% |
| A harmless extra sentence, no instruction in it (answers changed) | 34 queue, 35 priority | against a no-edit floor of 13 and 6 |
| Constrain output to valid labels: priority-to-high | 67.3% vs 67.2% | a valid label is still a valid label |
| Markers plus data note: direct command to queue | 33.0% to 6.4% | the one cell where it clearly worked |
| Markers plus data note: polite sentence to queue | 71.2% to 72.4% | no effect |
| Markers plus data note: priority-to-high, mean of three | 67.2% to 65.0% | a 2.2-point reduction |
| Invalid outputs | 0 in every arm |
The short version
Any system that lets a model read text written by someone else, tickets, emails, form fields, reviews, has the same weakness: the text can contain a sentence addressed to the model. I wanted to know how easily that works on a small local model, and whether the usual defences help. All six use the same setup: the open Qwen3.5-9B model compressed to 4 bits, run through llama.cpp on one 16 GB RTX 5060 Ti, at temperature 0 (the setting that makes a model as repeatable as it gets), on 500 customer-support tickets. Each experiment's questions, thresholds and analysis were written down before it was run.
- It works, and the polite version works best. A single appended sentence moved the queue answer to a named team on 71.2% of 500 tickets. A blunt command moved 33.0%. A sentence worded as if from an authority moved only 3.6% on that target, though it worked on priority.
- It does not need to be an instruction. A harmless extra sentence with no request in it changed 34 queue answers, against 13 that change when nothing is added. The model is easy to nudge.
- Making the output a valid label does nothing. Forcing the model to answer with one of the allowed priorities left the attack at 67.3%, against 67.2% without it. A wrong label is still a valid label.
- Marking the ticket as data helped on one attack only. The blunt command fell from 33.0% to 6.4% with markers and a data note (5.4% with markers alone). The polite sentence stayed at 71%.
Takeaway: if a model's answer decides where something goes or how urgent it is, assume a stranger can steer it with one sentence, keep a person or a second check on the answers that matter, and test your defence against more than one wording before trusting it.
What I tested
The task is the one from part 1: a support ticket, asked "which team handles this?" (ten options) and "how urgent?" (low, medium, high). I appended one sentence to the ticket text and counted how often the answer moved to what the sentence asked for. There were three wording styles (a direct command, an authority-styled note, a friendly request) and two targets (route to a specific team; mark as high priority). To avoid handing out a recipe I am not publishing the sentences.
The four defences were: nothing; restrict the output to valid labels; put the ticket between markers with a note that its contents are data, not instructions; both together.
Results: undefended
| Sentence style | Routed to the target team | Marked high priority |
|---|---|---|
| Direct command | 165 of 500 (33.0%) | 321 (64.2%) |
| Authority-styled | 18 (3.6%) | 346 (69.2%) |
| Friendly request | 356 (71.2%) | 341 (68.2%) |
Five of the six sentences moved more than 10% of tickets. For comparison, the model was only 32% accurate on routing and 40% on priority in the first place.
Results: the defences
| None | Valid labels only | Markers + data note | Both | |
|---|---|---|---|---|
| Priority to high, mean of 3 styles | 67.2% | 67.3% | 65.0% | 65.2% |
| Routing, direct command | 33.0% | 33.8% | 5.4% | 6.4% |
| Routing, authority-styled | 3.6% | 4.4% | 7.2% | 7.2% |
| Routing, friendly request | 71.2% | 71.0% | 72.4% | 73.0% |
The markers defence has a narrow benefit: it stopped the blunt command from working on routing, and that is the case a quick test would most likely try. A tester who checked only that one would conclude the defence works. The friendly wording, which is also the one that works best undefended, was untouched.
What I would not claim
- One model, one ticket set, and six sentences. "The friendly style beats the blunt one" is about these six sentences, not about social engineering in general. The 3.6% authority result is probably about that specific sentence and team.
- These runs carry the same-prompt noise floor from part 1 (about 21 in 500 for routing), so small differences are not meaningful.
- The marker defence tested is one specific wording of it. A different one could do better.
Part 2 of 6. Previous: how much changes when you change nothing. Next: what the model does when the answer isn't in the text.
Cite this research
Bart Porcincula. "One Polite Sentence Redirected a Small AI Classifier on 71% of Tested Tickets." Published 2026-10-29; updated 2026-10-29. https://porsync.com/research/one-appended-sentence-redirects-small-model-ticket-sorting
Permanent article URL