# METR exposed vibe-coded agent dashboard key leading to $600K credit theft

- ID: metr-vibe-coded-agent-dashboard-2026-08
- Reported: 2026-08-31
- Researcher: METR
- Organization: METR (Model Evaluation and Threat Research)
- AI role: ai_credential_theft (AI credential theft)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-11-05
- Entry page: https://openattacks.ai/attacks/metr-vibe-coded-agent-dashboard-2026-08/
- Entry JSON: https://openattacks.ai/api/attacks/metr-vibe-coded-agent-dashboard-2026-08.json
- Browse title: METR exposed vibe-coded agent dashboard key leading to $600K credit theft
- Editorial summary: Aug 31, 2026: METR disclosed incident where 'vibe-coded' (minimally tested, rapidly prototyped) AI agent dashboard accidentally exposed API key in client-side code. Unknown actor discovered key, used AI…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/metr-vibe-coded-agent-dashboard-2026-08.json

## Technique
Aug 31, 2026: METR disclosed incident where 'vibe-coded' (minimally tested, rapidly prototyped) AI agent dashboard accidentally exposed API key in client-side code. Unknown actor discovered key, used AI tooling to rapidly enumerate victim's cloud AI accounts (AWS Bedrock, Azure OpenAI, GCP Vertex AI), and drained approximately $600,000 in AI inference credits via unauthorized LLM calls. Demonstrates security risks of rapid AI prototyping ('vibe-coding') and AI-augmented attacker enumeration. METR estimates AI tooling accelerated enumeration ~10x vs manual methods.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Exposed API key in vibe-coded dashboard client-side code

## AI tooling and models
- AI-assisted cloud account enumeration
- Automated credential abuse

## Other tooling
- API key harvesting
- Cloud AI credit draining

## Victims and sectors
METR organization; AI research

## Target geography
- United States

## Attribution
Unknown actor

## Scale and metrics
~$600,000 in AI credits stolen over \<24 hours

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### discover-key: Discover exposed API key [access]
Actor finds API key exposed in vibe-coded dashboard client-side code
Evidence: https://metr.org/blog/2026-08-31-security-update/

### ai-enumeration: AI-assisted account enumeration [ai]
Use AI tooling to rapidly enumerate cloud AI accounts (AWS Bedrock, Azure OpenAI, GCP Vertex AI); ~10x faster than manual
Evidence: https://metr.org/blog/2026-08-31-security-update/

### drain-credits: Drain AI inference credits [impact]
Make unauthorized LLM inference calls across enumerated accounts, draining ~$600K in credits
Evidence: https://metr.org/blog/2026-08-31-security-update/

Connections:
- discover-key -> ai-enumeration
- ai-enumeration -> drain-credits

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### discover-key: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### ai-enumeration: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### drain-credits: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0000: Search Open Technical Databases — Exposed API key in AI agent dashboard leads to theft of AI inference credits
  Technique: https://atlas.mitre.org/techniques/AML.T0000
  Evidence: https://metr.org/blog/2026-08-31-security-update/

## Defensive notes
Secure AI prototypes before production; never expose API keys in client code; use secret management; monitor AI usage for anomalies; set usage limits

## Sources
- https://metr.org/blog/2026-08-31-security-update/ — METR: Exposed Vibe-Coded Agent Dashboard Key Led to ~$600K Credit Theft

## Source notes
METR disclosure. 'Vibe-coding' refers to rapid AI-assisted prototyping with minimal security review. Detection: monitor for unusual AI credit consumption spikes, unauthorized account access, rapid enumeration patterns.

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [],
  "ips": [],
  "hashes": [],
  "urls": []
}
```
