Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| pydantic | pydantic-ai-harness | unaffected |
|
No data.
No data.
| Vendor | Product | Versions | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Pydantic | Pydantic-ai |
|
| Source | ID | Title |
|---|---|---|
Github GHSA |
GHSA-3589-pxp7-3gj8 | Pydantic AI Harness tool-call limit bypass in nested CodeMode calls |
No CVSS v3.0
No CVSS v2
This CVE is not in the KEV list.
Exploit prediction score: < 1% (0.346% probability within 30 days)
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Pydantic
Pydantic pydantic-ai |
|
| Vendors & Products |
Pydantic
Pydantic pydantic-ai |
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
ssvc
|
| Type | Values Removed | Values Added |
|---|---|---|
| Description | Pydantic AI Harness before 0.59.0 fails to enforce UsageLimits.tool_calls_limit on nested tool calls dispatched from run_code in the CodeMode toolset. Users or prompt-injected content can make the sandboxed program invoke tools via run_nested_call() without check_before_tool_call, exceeding operator limits on costly or side-effecting tools. | |
| Title | Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code | |
| Weaknesses | CWE-770 | |
| References |
|
|
| Metrics |
cvssV3_1
|