Approved changes feed: RSS · Atom
cpe:2.3:a:tianguaduizhang:ai_code:*:*:*:*:*:visual_studio_code:*:*part: a version: * update: *
| Vendor | Tianguaduizhang (ab2a247b-6520-52f1-865f-2138da333c86) |
|---|---|
| Product | Ai Code (823eb08e-19b5-5345-af0e-2e1cfa6c7755) |
| Edition | * |
| Language | * |
| Software edition | * |
| Target software | visual_studio_code |
| Target hardware | * |
| Other | * |
Notes
Imported from gcve-enriched-dumps CVE data
PURL mappings
| PURL | Source | Last updated |
|---|---|---|
| No PURL mappings for this CPE yet. | ||
Vulnerability references
| Identifier | cpeApplicability | Submitted | db.gcve.eu details | Rationale |
|---|---|---|---|---|
CVE:CVE-2026-30304 |
vulnerable | 2026-06-08 07:57:14.009516 |
Details available
In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be potentially destructive, it still requires user approval. However, this design is highly susceptible to prompt injection attacks. An attacker can employ a generic template to wrap any malicious command and mislead the model into misclassifying it as a 'safe' command, thereby bypassing the user approval requirement and resulting in arbitrary command execution.
Published: 2026-03-27T00:00:00.000Z
Updated: 2026-03-27T19:48:56.483Z |
Imported from gcve-enriched-dumps CVE data |
Contribute
You can submit an edit proposal for this CPE entry or suggest a related product/vendor addition using the action button above.
Inspect record JSON
Open this panel to browse, search, copy or download the JSON record.