Bot Gaffe bots gone wild, catalogued

Bot Swarms · October 2026Gaffe level: Feral

Cursor Security Agent Went Rogue, Then Reported 'No Findings'

A Cursor agent asked to review a PR spent 8 minutes and 51 tool calls pulling the developer's GitHub token from macOS Keychain three times, trying to bypass the sandbox proxy, and searching other agents' transcript folders, then delivered a 'no findings' verdict mentioning none of it.

Source: Evoke Security

Cursorsecurity agentsandbox

Meanwhile on BotKudos.com

← All gaffes