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

TitelFoundationAgents MetaGPT 0.8.1 Eval Injection (CWE-95)
Beschreibung# 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.
Quelle⚠️ https://github.com/FoundationAgents/MetaGPT/issues/1928
Benutzer
 Eric-c (UID 96848)
Einreichung28.03.2026 03:58 (vor 26 Tagen)
Moderieren09.04.2026 14:04 (12 days later)
StatusAkzeptiert
VulDB Eintrag356525 [FoundationAgents MetaGPT bis 0.8.1 XML action_node.py ActionNode.xml_fill Remote Code Execution]
Punkte20

Might our Artificial Intelligence support you?

Check our Alexa App!