提交 #791734: FoundationAgents MetaGPT 0.8.1 Eval Injection (CWE-95)

# Technical Details
A Code Injection (Eval Injection) vulnerability exists in the `xml_fill` method of `metagpt/actions/action_node.py` in MetaGPT.

The application uses the unsafe `eval()` function to parse strings from LLM responses into Python objects for `list` and `dict` field types. An attacker who can influence the LLM's output (e.g. via prompt injection) can inject arbitrary Python code which is then executed on the server.

# Vulnerable Code
File: metagpt/actions/action_node.py
Method: ActionNode.xml_fill
Why: When extracting fields of type `list` or `dict`, the extracted regex match `raw_value` is directly passed to `eval(raw_value)` without sanitization (e.g. using `ast.literal_eval`).

# Reproduction
1. In MetaGPT, initialize an ActionNode with `expected_type=list` or `dict`.
2. Construct a prompt injection payload that forces the LLM to output a malicious XML tag, e.g.:
`<FileExtraction>__import__('os').system('touch /tmp/verify_rce') or ['pwned']</FileExtraction>`
3. Process the context using `node.xml_fill(context)`.
4. The `eval()` function executes the payload. Verify `/tmp/verify_rce` exists on the host.

# Impact
- Remote Code Execution (RCE): An attacker capable of performing Prompt Injection can force the LLM to output a malicious XML tag. When processed, this executes arbitrary commands, allowing the attacker to access sensitive files or compromise the host system.

• 来源: ⚠️ https://github.com/FoundationAgents/MetaGPT/issues/1928
• 用户: Eric-c (UID 96848)
• 提交: 2026-03-28 03時58分 (6 月前)
• 管理: 2026-04-09 14時04分 (12 days later)
• 状态: 已接受
• VulDB条目: 356525 [FoundationAgents MetaGPT 直到 0.8.1 XML action_node.py ActionNode.xml_fill 远程代码执行]
• 积分: 20