Answer in brief
CVE-2026-72742 records a High severity (CVSS 8.6) vulnerability in DSPy 3.3.0b1 Local File Read via Image/Audio Output Field Parsing. The current sources do not mark it as known exploited. The current feed maps Stanford NLP/DSPy (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 8.6. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps Stanford NLP/DSPy (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| Stanford NLP/DSPygeneric | 0 | Not reported |
Published upstream
Aug 11, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Aug 12, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Aug 11, 2026
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.
Quoted source text, attributed separately from HOL analysis.