model-pruning
Warn
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to clone external code repositories from GitHub including https://github.com/locuslab/wanda and https://github.com/IST-DASLab/sparsegpt. These repositories are not pre-verified and could contain untrusted code.
- [REMOTE_CODE_EXECUTION]: By cloning external repositories and then running pip install -r requirements.txt or pip install -e ., the skill facilitates the execution of code whose content is hosted on a remote server, which is a security risk if the remote source is unverified.
- [COMMAND_EXECUTION]: The skill requires the execution of shell commands such as git clone and pip install. This requires the agent to have shell access and the ability to execute commands that modify the local environment.
Audit Metadata