Unknown Agent
AI Agent Reliability Report
Failure Modes
Root Causes
Frequently Asked Questions
Is Unknown Agent reliable?
Based on 4 documented incidents, Unknown Agent has an average failure severity of 8.5/10. 3 incidents were rated critical and 0 were rated high severity. Common failure modes include security vulnerability.
What are the most common Unknown Agent failures?
The most frequently documented Unknown Agent failure modes are: security vulnerability (3 incidents), infinite loop (1 incidents). These failures range from critical to high severity.
How many Unknown Agent AI failures have been documented?
StupidLLM has documented 4 Unknown Agent AI agent failures. Each incident is severity-scored on a 0-10 scale, verified against source evidence, and categorized by failure mode and root cause.
All Unknown Agent Incidents
AI vibe-coded Next.js app pinned vulnerable dependency — cryptominer compromised production server
A developer used an AI coding agent to build a Next.js web service via 'vibe coding' (building from functional descriptions). The agent pinned a dependency version that contained C
Vibe-coded Moltbook exposed 1.5M API keys and 35,000 user emails via misconfigured database
Moltbook, an application built through AI 'vibe coding', exposed roughly 1.5 million API keys and 35,000 user email addresses directly to the public internet. The cause was a misco
Vibe-coded Tea app leaked 72,000 IDs and selfies plus 1.1M private messages from an unsecured bucket
Tea, a women-only dating-safety app, suffered two breaches in July 2025 that a hacker attributed to 'vibe coding' — heavy reliance on AI tools to ship product without security revi
An AI agent spun up duplicate CloudFormation stacks on every error and ran up a $6,531 AWS bill
On June 12, 2026, an AI agent tasked with something as minor as registering for the DN42 hobbyist network ran up a $6,531.30 AWS bill. Its failure strategy was the problem: every t