run-experiment
Facilitates deployment and execution of ML experiments on local or remote GPU servers, optimizing resource usage and workflow.
Install this skill
or
93/100
Security score
The run-experiment skill was audited on May 23, 2026 and we found 3 security issues across 2 threat categories. Review the findings below before installing.
Categories Tested
Security Issues
medium line 187
Access to hidden dotfiles in home directory
SourceSKILL.md
| 187 | After deployment is verified, check `~/.claude/feishu.json`: |
low line 261
External URL reference
SourceSKILL.md
| 261 | > **Vast.ai setup**: Run `pip install vastai && vastai set api-key YOUR_KEY`. Upload your SSH public key at https://cloud.vast.ai/manage-keys/. Set `gpu: vast` in your `CLAUDE.md` — `/run-experiment` |
low line 263
External URL reference
SourceSKILL.md
| 263 | > **W&B setup**: Run `wandb login` on your server once (or set `WANDB_API_KEY` env var). The skill reads project/entity from CLAUDE.md and adds `wandb.init()` + `wandb.log()` to your training scripts |
Scanned on May 23, 2026
View Security DashboardGitHub Stars 1.2K
Rate this skill
Categorydevelopment
UpdatedJune 10, 2026
brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research