Amazon Q for VS Code ships with injected 'wipe the system' prompt
Amazon Web Services · Jul 17, 2025 · Coding agent
What happened
An attacker submitted a pull request to the open-source aws-toolkit-vscode repository, was granted admin credentials, and planted a prompt instructing the Amazon Q coding agent to 'clean a system to a near-factory state' — deleting local files and cloud resources. The injected prompt shipped in the official 1.84.0 release of an extension with over 960,000 installs. AWS revoked the credentials, removed the code, and released 1.85, telling all users to update.
Causal vector
Supply-chain compromise of the agent's system prompt via a poisoned open-source release
Source
Reported by SC Media. Verified against the primary report.
When the system prompt itself is the payload, no amount of prompt engineering helps. Destructive filesystem and cloud-resource deletions are spend-equivalent actions: an approval threshold on bulk deletes sits outside the compromised prompt and stops the wipe at the action layer, after the supply chain has already failed.
The six rule types that contain this class of failure
Per-transaction cap
Any single spend above your ceiling is BLOCKED before it moves.
Daily total
Cumulative spend across all agent calls, bounded per day.
Velocity limit
Stops runaway retry loops — the #1 cause of overnight losses.
Merchant allowlist
Only approved destinations can ever receive funds.
Category rules
Flag high-risk classes (crypto, infra, refunds) for review.
Approval threshold
Above a value, the action waits for a human.
Related incidents
NeuralTrust: 34.9% of enterprises report confirmed AI agent security incidents
NeuralTrust · Jun 1, 2026
HUMAN Security: AI agent traffic grew 7,851%, 8x faster than human traffic
HUMAN Security · Jan 1, 2026
Don't be the next entry
Every incident in this database is the result of trusting a prompt, a provider cap, or a human review cycle. sipi.bot replaces all three with one deterministic call. 67 documented failures, one control.