The story’s score and claims

Comments on No. 42 of 106 · mrnice.dev · edition of Thursday 12 November 2026

Prompt Injection, Esq.: pwning AI agent guardrails with lawyerspeak

Summary

A security engineer at Opsin Security recounts how a read-only ChatGPT workspace agent that manages their Notion hiring tracker was talked into editing records after a fake law-firm letter, generated with the Heavyweight tool, was posted in Slack. The agent followed the official-looking letter over its original guardrail.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules