The OpenAPI and ChatGPT plugin loaders in LlamaHub (aka llama-hub) before 0.0.67 allow attackers to execute arbitrary code because safe_load is not used for YAML.
https://github.com/run-llama/llama-hub/releases/tag/v0.0.67
https://github.com/run-llama/llama-hub/pull/841/commits/9dc9c21a5c6d0226d1d2101c3121d4f085743d52
https://github.com/run-llama/llama-hub/blob/v0.0.67/CHANGELOG.md