Amp Code: Invisible Prompt Injection Fixed by Sourcegraph
The post describes an invisible prompt injection vulnerability in Amp, a coding agent from Sourcegraph, where invisible Unicode Tag characters were interpreted as instructions.
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 model Amp uses was not confirmed by the author, who assumed Claude or Gemini.
One primary source; other links are context, not independent corroboration.
- Primary sourceembracethered.com
- Linked in sourceinvisible instructions impact Google Jules
- Linked in sourcequite a bit in the past
- Linked in sourcewas discovered by Riley Goodside with ChatGPT
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 post describes an invisible prompt injection vulnerability in Amp, a coding agent from Sourcegraph, where invisible Unicode Tag characters were interpreted as instructions. The author reports an end-to-end exploit that triggered a grep for an environment variable, encoded it into a URL query parameter, and exfiltrated it via web page reading or markdown image rendering. The author states the vulnerability was reported to Sourcegraph on June 14, 2025, and was quickly addressed, apparently by sanitizing input. The post also notes that several major model vendors' models interpret these characters as instructions, while OpenAI mitigated it at the model/API layer.
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 model Amp uses was not confirmed by the author, who assumed Claude or Gemini.
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 model Amp uses was not confirmed by the author, who assumed Claude or Gemini.
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 was vulnerable to interpreting invisible Unicode Tag characters embedded in text as instructions.
Source: embracethered.com ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseAn end-to-end exploit chained a grep for an environment variable, URL encoding of that value, and exfiltration via read_web_page or markdown image rendering.
Source: embracethered.com ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseThe author reports Sourcegraph was contacted June 14, 2025, and the issue was quickly addressed, apparently by input sanitization.
Source: embracethered.com ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the model Amp uses was not confirmed by the author, who assumed Claude or Gemini.
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 model Amp uses was not confirmed by the author, who assumed Claude or Gemini.
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
Applications built on LLMs that accept untrusted text may be hijacked through invisible characters, leading to secret leakage. Developers should strip or neutralize these characters and limit downstream exfiltration paths.
Limits and open questions
Source claims not independently checked; the model Amp uses was not confirmed by the author, who assumed Claude or Gemini.
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 →