CVE-2026-72742DSPy 3.3.0b1 Local File Read via Image/Audio Output Field Parsing
Updated under an hour ago ()
Does this affect you?
It affects Stanford NLP DSPy. Add what you run to find out whether that includes you.
No exploitation reported and no EPSS estimate yet.
Do this next
Free account, 1 product
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.
- CVSS
- 8.6 HIGH (v3.1, CNA)CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N
- Weakness (CWE)
- CWE-73
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- Not loaded for this CVE
- Assigned by
- VulnCheck
- NVD analysis
- Awaiting Analysis
- Record last updated
- Aug 12, 2026
- First seen by InfoSec Signals
- Oct 9, 2026
Affected products
Stanford NLP DSPy stanford_nlp:dspy (from the name) | through 3.3.0b1 | CNA record |
References
- https://github.com/stanfordnlp/dspyproduct
- https://github.com/stanfordnlp/dspy/issues/10067issue-tracking
- https://github.com/stanfordnlp/dspy/commit/c69136b29aca4c00ca6da7667f7b80783188980epatch
- https://www.vulncheck.com/advisories/dspy-0b1-local-file-read-via-image-audio-output-field-parsingthird-party-advisory
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.