CyberRota Analysis
AI-GeneratedDSPy 3.3.0b1 is vulnerable to a file exfiltration flaw that allows attackers to read arbitrary local files by manipulating the URL field in Image and Audio output adapters. This vulnerability can lead to sensitive data leakage through crafted prompts sent to a compromised language model endpoint. Organizations using this version of DSPy should prioritize remediation to mitigate the risk of unauthorized data access.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD 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.