StupidLLM
The incident database for AI agent failures
According to StupidLLM's incident database, 64 AI agent failures have been documented across 27 agents like Devin, Cursor, Claude Code, GitHub Copilot, Windsurf, and Aider — with an average severity of 6.7/10. Like CVE for cybersecurity vulnerabilities, we assign STUPID-IDs to documented cases where AI agents cause real damage — deleted files, security vulnerabilities, infinite loops, wasted resources, and broken production systems.
Latest Incidents
Gemini CLI silently executed arbitrary code from an untrusted repo (CVE-2026-12537, CVSS 10.0)
Malicious cloned repository triggered code execution in Cursor on Windows
GPT-5.6-Sol 'accidentally deleted almost ALL' of a tester's Mac files during OpenAI's Ultra mode trial
Cursor AI agent deleted PocketOS's entire production database and backups in 9 seconds
Replit AI agent wiped SaaStr's production database during a code freeze, then hid the rollback
The runaway-cost pattern, quantified: agentic coding tools burn 10-100x more tokens and can rival developer pay
An AI agent spun up duplicate CloudFormation stacks on every error and ran up a $6,531 AWS bill
Salesforce Agentforce hit a 77% B2B failure rate — and Salesforce admitted it was 'more confident than we should have been'
Two AI agents ping-ponged for 11 days and ran up a $47,000 bill — neither noticed anything wrong
Cyera study: 344 verified enterprise agent-damage cases, 188 with no attacker involved
Highest Severity
Gemini CLI silently executed arbitrary code from an untrusted repo (CVE-2026-12537, CVSS 10.0)
Malicious cloned repository triggered code execution in Cursor on Windows
GPT-5.6-Sol 'accidentally deleted almost ALL' of a tester's Mac files during OpenAI's Ultra mode trial
Cursor AI agent deleted PocketOS's entire production database and backups in 9 seconds
Replit AI agent wiped SaaStr's production database during a code freeze, then hid the rollback
Most Tracked Agents
What is StupidLLM?
According to StupidLLM's incident database, 64 AI agent failures have been documented across 27 agents with an average severity of 6.7/10. Every incident is severity-scored using our CVSS-inspired rating system, verified against source evidence, and searchable by agent, failure mode, and root cause. We track reliability trends across agents so developers and enterprises can make informed decisions about which AI tools to trust.
How are AI agent incidents scored?
Every incident is severity-scored on a 0-10 scale using a CVSS-inspired rating system. Scores of 9-10 are critical, 7-8 are high, 4-6 are medium, and 0-3 are low severity. Incidents are verified against source evidence and categorized by failure mode and root cause.
Which AI coding agent has the most failures?
Visit the StupidLLM dashboard for live rankings of AI agent failure rates. We track 64 incidents across 27 agents with average severity scores and risk levels.
AI Agent Failure Modes
Hallucination
Agent invents APIs, functions, or files that don't exist
Destructive Action
Agent deletes files, drops tables, or corrupts data
Infinite Loop
Agent gets stuck retrying the same failed approach
Security Vulnerability
Agent introduces XSS, SQL injection, or leaked secrets
Scope Explosion
Agent rewrites far more code than requested
Data Loss
Agent causes irreversible loss of user or system data