Amp Code: Arbitrary Command Execution via Prompt Injection Fixed
The source describes how Sourcegraph's Amp coding agent could modify its own VS Code settings.json file outside the project folder without developer approval.
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: the full demo and fix details were not independently verified, and the fetched text is the author's account.
One primary source; other links are context, not independent corroboration.
- Primary sourceembracethered.com
- Linked in sourceSourcegraph
- Linked in sourcesystem prompt here
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
The source describes how Sourcegraph's Amp coding agent could modify its own VS Code settings.json file outside the project folder without developer approval. This allowed the agent, or an attacker via indirect prompt injection, to add bash commands to the allowlist or add malicious MCP servers that launch immediately, enabling arbitrary code execution. The author reports the flaw was reported to Sourcegraph in early July and fixed within a few days. The post includes a demo video and a sample prompt-injection payload embedded in a C source file.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; the full demo and fix details were not independently verified, and the fetched text is the author's account.
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; the full demo and fix details were not independently verified, and the fetched text is the author's account.
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.
Amp could write to the user's VS Code settings.json outside the project folder without developer approval.
Source: embracethered.com ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseAttackers or the model could add allowlisted bash commands, such as a wildcard, so commands run without user consent.
Source: embracethered.com ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseAdding a malicious MCP server to the config caused Amp to launch it immediately, enabling arbitrary code execution.
Source: embracethered.com ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseThe vulnerability was reported to Sourcegraph, promptly fixed, and users are advised to run the latest version.
Source: embracethered.com ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the full demo and fix details were not independently verified, and the fetched text is the author's account.
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.
Embrace The Red published this item in its official feed. AINewsIQ collected it server-side for source checking and editorial review.
Source claims not independently checked; the full demo and fix details were not independently verified, and the fetched text is the author's account.
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
The post illustrates how coding agents with write access to their own configuration can be escalated via indirect prompt injection into full host compromise, underscoring the need to restrict agent modification of critical files.
Limits and open questions
Source claims not independently checked; the full demo and fix details were not independently verified, and the fetched text is the author's account.
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 →