DSPy 3.3.0b1 Local File Read via Image/Audio Output Field Parsing
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| Stanford NLP | DSPy | affected |
|
No data.
No data.
| Vendor | Product | Versions | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Stanford Nlp | Dspy |
|
No CVSS v3.0
No CVSS v2
This CVE is not in the KEV list.
Exploit prediction score: < 1% (0.508% probability within 30 days)
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Stanford Nlp
Stanford Nlp dspy |
|
| Vendors & Products |
Stanford Nlp
Stanford Nlp dspy |
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
ssvc
|
| Type | Values Removed | Values Added |
|---|---|---|
| Description | DSPy 3.3.0b1 contains a file exfiltration vulnerability in the Image and Audio output field adapters that allows attackers with influence over language model outputs to read arbitrary local files by injecting a filesystem path into the url field of a parsed Image or Audio typed output. The JSONAdapter and ChatAdapter parse untrusted language model completions through parse_value into TypeAdapter validation, which triggers encode_image or encode_audio to read and base64-encode any local file path via the os.path.isfile branch in image.py and audio.py, subsequently embedding the file contents into outgoing prompt messages sent to the attacker-controlled model endpoint. | |
| Title | DSPy 3.3.0b1 Local File Read via Image/Audio Output Field Parsing | |
| Weaknesses | CWE-73 | |
| References |
| |
| Metrics |
cvssV3_1
|