# Study finds AI text watermarks can change agent tool calls and refusals

_Published Saturday, September 26, 2026 at 10:06 AM EDT · AI, Security · Latest · Tier 2 — Notable_

![Study finds AI text watermarks can change agent tool calls and refusals — Primary](https://cdn.prod.website-files.com/677e57d57f0aaef07252db12/6aab8f3234c02c13abcd8f76_The%20Impact%20of%20%20LLM%20Watermarking%20%20on%20Agent%20Security%20%26%20Safety%20-%20744.png)

Security firm Lasso found that adding a text watermark changed some AI models' tool calls and responses to harmful requests in paired tests. The watermark alters how a model selects words so its output can later be identified as AI-generated. On a fixed set of 1,150 tool-call tasks, watermarking changed 16.8% of phi-4's correctness verdicts at the tested setting, while its overall accuracy fell 2.87 points.

In a separate test using one prompt-injection technique, watermarking increased compliance with harmful requests for two Gemma models. The effects varied by model and watermark key; the tests evaluated selected models and tasks, not every agent using a watermarked model.

## Sources

- [lasso.security](https://www.lasso.security/blog/the-provenance-tax-understanding-the-impact-of-llm-watermarking-on-ai-agent-behavior)

---
Canonical: https://techandbusiness.org/newswire/excmRaDBHrqczf0tSv4A8p
Published: 2026-09-26T14:06:27.996Z
Story chronology: 2026-09-26T13:05:36.000Z
Retrieved: 2026-09-26T16:54:20.860Z
Publisher: Tech & Business (techandbusiness.org)