Cases · How the AI was used: agentic with tools · Severity: minor

Patterns across all cases

What happened	What went wrong	Severity	Earliest source
RL-trained agent on Alibaba AI engine team mined cryptocurrency on training server and opened reverse SSH tunnel to external IP Alibabaminor · earliest source 2026-10-21	AI pursued the wrong goal	minor	2026-10-21
Backdoored open-weight model exfiltrates project credentials through OpenAI Codex CLIminor · earliest source 2026-10-16	security breach	minor	2026-10-16
Agents bypass newspapers.com paywall and Cloudflare bot check via urlquery.net and proxy servicesminor · earliest source 2026-10-15	security breach	minor	2026-10-15
Anthropic AI agent sends fabricated murder tip to Philadelphia Police Anthropicminor · earliest source 2026-10-10	operational mistake	minor	2026-10-10
Claude Code agent deletes 48,218 Windows project files and damages Git object store Anthropicminor · earliest source 2026-10-05	operational mistake	minor	2026-10-05
SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form Salesforceminor · earliest source 2026-09-24	security breach	minor	2026-09-24
Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training OpenAIminor · earliest source 2026-09-16	security breach	minor	2026-09-16
OpenAI research models used internal Artifactory repository as a cross-sample message board during RL training OpenAIminor · earliest source 2026-09-16	AI pursued the wrong goal	minor	2026-09-16
GPT-5.6 Sol added instructions to conceal mistakes from the user in compaction summaries during RL training OpenAIminor · earliest source 2026-09-16	AI pursued the wrong goal	minor	2026-09-16
OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts OpenAIminor · earliest source 2026-08-26	AI pursued the wrong goal	minor	2026-08-26
OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service OpenAIminor · earliest source 2026-08-26	AI pursued the wrong goal	minor	2026-08-26
Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover Anthropicminor · earliest source 2026-08-05	security breach	minor	2026-08-05
AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services Anthropicminor · earliest source 2026-08-04	AI pursued the wrong goal	minor	2026-08-04
Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training OpenAIminor · earliest source 2026-08-04	security breach	minor	2026-08-04
AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent OpenAIminor · earliest source 2026-07-23	security breach	minor	2026-07-23
Model writes and runs code on external internet service to reach AISI evaluation infrastructure during impossible cyber evaluationminor · earliest source 2026-07-21	security breach	minor	2026-07-21