ai-for-science-oligoformer

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly directs cloning a public GitHub repo (https://github.com/lulab/OligoFormer.git) and downloading an RNA-FM tarball via wget from cloud.tsinghua.edu.cn, and then running those third-party scripts/code as part of inference/training, meaning untrusted external content is fetched and executed and can influence subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly runs git clone https://github.com/lulab/OligoFormer.git and wget 'https://cloud.tsinghua.edu.cn/f/46d71884ee8848b3a958/?dl=1' (and uses the external pip index https://repo.huaweicloud.com/repository/pypi/simple/) at runtime to fetch code/packages (the RNA-FM tarball and repository) that are required and later executed/imported, so these URLs constitute runtime external dependencies that fetch and execute remote code.