Skip to main content

evaluating-cosmos-policy

Evaluates NVIDIA Cosmos Policy in LIBERO and RoboCasa environments, optimizing robot manipulation and profiling GPU performance.

Install this skill

or
38/100

Security score

The evaluating-cosmos-policy skill was audited on Jun 8, 2026 and we found 6 security issues across 3 threat categories, including 2 critical. Review the findings below before installing.

Categories Tested

Security Issues

critical line 69

Eval function call - arbitrary code execution

SourceSKILL.md
69| LIBERO smoke eval (1 trial) | 1x A40/A100 | ~16 GB | 5-10 min |
critical line 70

Eval function call - arbitrary code execution

SourceSKILL.md
70| LIBERO full eval (50 trials) | 1x A40/A100 | ~16 GB | 2-4 hours |
medium line 173

Template literal with variable interpolation in command context

SourceSKILL.md
173```bash
medium line 308

Template literal with variable interpolation in command context

SourceSKILL.md
308```bash
low line 358

Access to hidden dotfiles in home directory

SourceSKILL.md
358config_dir = os.path.expanduser("~/.libero")
low line 402

External URL reference

SourceSKILL.md
402- MuJoCo documentation: https://mujoco.readthedocs.io/
Scanned on Jun 8, 2026
View Security Dashboard
Installation guide →
GitHub Stars 9.4K
Rate this skill
Categorydevelopment
UpdatedJune 10, 2026
Orchestra-Research/AI-Research-SKILLs