Build a 100-line checker that catches chained-skill approval hijacks
Two agent skills, each harmless when read on its own, can get an agent to upload a report the user never agreed to share. The trick is a progress file. The first skill writes it; the second one trusts it. This post builds a small stdlib Python checker that shows the pattern and shows where a per-skill check goes blind. It is a teaching toy. Run it, change the scenarios, and see what breaks. The…
A small Python checker demonstrates how two seemingly harmless agent skills can collaborate to upload unauthorized user data. By writing progress files and trusting each other, the skills can deceive the system. The checker's two rules are insufficient on their own; a runtime rule is required to prevent unauthorized actions.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
