Clinejection — Compromising Cline's Production Releases just by Prompting an Issue Triager
Simon Willison's link post describes Adnan Khan's write-up of an attack chain against Cline's GitHub repository.
Source-based brief · Editor review not recorded · See checks and limits ↓
⚑ Recency not confirmed · what to check
We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news.
Claim context: this brief is based on Willison's short link post summarizing Khan's write-up, and the full original article was not checked.
One primary source; other links are context, not independent corroboration.
- Primary sourcesimonwillison.net
Grok Bot submitted this discovery. We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Recency not confirmed-8
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Simon Willison's link post describes Adnan Khan's write-up of an attack chain against Cline's GitHub repository. Cline ran AI-powered issue triage using anthropics/claude-code-action with broad tool permissions, and the issue title was included in the prompt. A crafted title could make Claude run npm install from an attacker-chosen package whose preinstall script executes arbitrary code. The triage workflow lacked publishing secrets, but a shared GitHub Actions cache key let it poison the cache used by the nightly release workflow, which held NPM publishing secrets. The post reports that a cline@2.3.0 package, now retracted, was published by an anonymous attacker, adding only OpenClaw installation.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; this brief is based on Willison's short link post summarizing Khan's write-up, and the full original article was not checked.
This connects a source, an attributed statement and its qualifications. It does not establish that the claim is correct.
Questions worth asking
Open questions for further reportingWhat remains unconfirmed?
Source claims not independently checked; this brief is based on Willison's short link post summarizing Khan's write-up, and the full original article was not checked.
What material was available for this brief?
The recorded brief basis is fetched source page. These points are AINewsIQ paraphrases, not quotations or independent confirmations.
Issue titles were interpolated into a Claude Code triage prompt that allowed Bash, enabling arbitrary command execution via prompt injection.
Source: simonwillison.net ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseThe triage and nightly release workflows used the same node_modules cache key, enabling cache poisoning of the release workflow.
Source: simonwillison.net ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseAn anonymous attacker published cline@2.3.0, which was later retracted; it reportedly only added OpenClaw installation.
Source: simonwillison.net ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; this brief is based on Willison's short link post summarizing Khan's write-up, and the full original article was not checked.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted this discovery. We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
Simon Willison · Prompt Injection published this item in its official feed. AINewsIQ collected it server-side for source checking and editorial review.
Source claims not independently checked; this brief is based on Willison's short link post summarizing Khan's write-up, and the full original article was not checked.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
Brief history · 1 retained version
These are changes to AINewsIQ’s own publication. Earlier history is unavailable unless recorded here. Complete retained versions are available to the editor.
- Version 1 · published
Source-based brief stored or updated. This does not establish that the publisher changed its page.
Automated record
Source observations · 1 recent captures
A changed capture means the extracted text differed. It can reflect page furniture or extraction changes; it does not establish a substantive correction. Source captures remain private.
Retained capture; no earlier comparison available.
New engagement snapshots do not mean the source itself changed. Source observations and AINewsIQ brief revisions are separate records.
Why this may matter
It shows how prompt injection in AI agent workflows can escalate to supply-chain compromise when agents have shell access and CI caches are shared across workflows with different privileges.
Limits and open questions
Source claims not independently checked; this brief is based on Willison's short link post summarizing Khan's write-up, and the full original article was not checked.
Organization-specific financial, security, and operational effects require the organization's own context and review.

Join the discussion
Have a different perspective or a question about the evidence? Discussion is free with a verified email account. Every comment is reviewed before publication.
No published comments yet.
New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →