๐Ÿ” CVE Alert

CVE-2026-72742

HIGH 8.6

DSPy 3.3.0b1 Local File Read via Image/Audio Output Field Parsing

CVSS Score
8.6
EPSS Score
0.0%
EPSS Percentile
0th

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.

CWE CWE-73
Vendor stanford nlp
Product dspy
Published Aug 11, 2026
Stay Ahead of the Next One

Get instant alerts for stanford nlp dspy

Be the first to know when new high vulnerabilities affecting stanford nlp dspy are published โ€” delivered to Slack, Telegram or Discord.

Get Free Alerts โ†’ Free ยท No credit card ยท 60 sec setup

CVSS v3 Breakdown

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N
Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Changed
Confidentiality
High
Integrity
None
Availability
None

Affected Versions

Stanford NLP / DSPy
0 โ‰ค 3.3.0b1

References

NVD โ†— CVE.org โ†— EPSS Data โ†—
github.com: https://github.com/stanfordnlp/dspy github.com: https://github.com/stanfordnlp/dspy/issues/10067 github.com: https://github.com/stanfordnlp/dspy/commit/c69136b29aca4c00ca6da7667f7b80783188980e vulncheck.com: https://www.vulncheck.com/advisories/dspy-0b1-local-file-read-via-image-audio-output-field-parsing

Credits

George Chen