AI Security Threat Feed

picklescan: RCE bypass enables ML supply chain attack

picklescan: security bypass enables RCE in ML pipelines

picklescan: detection bypass allows malicious pickle RCE

picklescan: detection bypass allows RCE via ML model files

picklescan: RCE bypass via idlelib SetText evasion

picklescan: scanner bypass enables RCE in ML models

picklescan: scanner bypass enables RCE via ML models

picklescan: scan bypass allows RCE in ML pipelines

picklescan: scanner bypass enables RCE in ML pipelines

picklescan: bypass enables undetected RCE in ML models

picklescan: PyTorch gadget bypasses scanner, enables RCE

picklescan: PyTorch gadget bypasses pickle RCE detection

picklescan: detection bypass via PyTorch proxy RCE

picklescan: RCE bypass via torch.utils.collect_env

picklescan: scanner bypass enables RCE via PyTorch function

picklescan: detection bypass enables PyTorch model RCE

picklescan: PyTorch bypass allows undetected RCE

llama-index: DocugamiReader MD5 hash collision drops chunks

llama-index: JSONReader DoS via recursive JSON parsing

llama-index Obsidian reader: hardlink path traversal leaks files