Aletheia: Permission-Minimality Testing for Coding-Agent Rules
- Occurred
- Sep 30, 2026
- Published
- Sep 30, 2026
- Source
- arXiv
Summary
Repository instruction files guide coding agents, but also expose them to prompt injection. Malicious rules can request credential access or data transfer while the agent produces a correct patch. We present Aletheia, a framework for permission-minimality testing. Aletheia translates requested authority into a typed language and synthesizes executable sandbox configurations. It runs the unchanged rule and task under full permissions and independent restrictions that remove one permission at a time. Passing independent functional tests under strictly reduced authority provides a dispensability witness, which Aletheia interprets against task context to diagnose suspicious requests. We formalize synthesis and the conditions connecting witnesses to enforced restrictions. On a shared refactoring task, Aletheia executes and detects all 314 AIShellJack attack inputs, with no alarms on five benign templates. Among 80 manually verified benign GHAgentFiles rules, it raises three false positives (3.75%).
Classification
Rationale: Framework detects prompt injection attacks on coding agents, a language model safety issue with limited harm.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8