LLMMedium
Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package
- Occurred
- Feb 17, 2026
- Published
- Feb 18, 2026
- Source
- AI Incident Database
Summary
An unknown actor reportedly exploited prompt injection in Cline's Claude-powered GitHub issue-triage workflow and a GitHub Actions cache-poisoning path to obtain publication credentials. On February 17, 2026, a still-valid npm token was used to publish unauthorized [email protected], which installed OpenClaw without user intent. Cline said OpenClaw was non-malicious; it deprecated the release and revoked the token that day, while reporting that it found no evidence of user-data exposure.
Developers
- Anthropic
- AI agent system developers
Deployers
- Cline Bot Inc.
- AI agent system deployers
- Threat actors
Harmed parties
- Cline Bot Inc.
- Cline CLI users
- Software developers
Tags
- response
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: Prompt injection in an LLM-powered workflow led to unauthorized package publication, but no user data exposure or major harm occurred.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8