提交 #784462: premsql v0.2.1 Code Injection信息

标题premsql v0.2.1 Code Injection
描述A Remote Code Execution (RCE) vulnerability exists in the premsql library due to the unsafe usage of eval() on language model outputs. An attacker can use prompt injection to force the LLM to output malicious Python code, which is then executed by the server. ```python try: result = self.generator.generate( data_blob={"prompt": prompt}, temperature=temperature, max_new_tokens=max_new_tokens, postprocess=False, ) # VULNERABILITY HERE: result = eval(result.replace("null", "None")) error_from_model = None assert "alternate_decision" in result assert "suggestion" in result ``` The `result` variable contains the raw string output from the LLM. The application attempts to parse this as a Python dictionary using `eval()`. However, if the LLM output is manipulated to contain valid Python commands (e.g., `__import__('os').system('calc')`), `eval()` will execute them.
来源⚠️ https://github.com/Ka7arotto/cve/blob/main/premsql-rce/issue.md
用户
 Goku (UID 80486)
提交2026-03-21 02時50分 (17 日前)
管理2026-04-05 07時12分 (15 days later)
状态已接受
VulDB条目355388 [premAI-io premsql 直到 0.2.1 followup.py eval result 权限提升]
积分20

Are you interested in using VulDB?

Download the whitepaper to learn more about our service!