evaluating-cosmos-policy
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.
72
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
The GitHub URLs for "moojink/robocasa-cosmos-policy" are personal/unverified forks used to distribute a Python package (via git clone / pip install -e) rather than an official vendor/org release, which matches high-risk indicators for executable distribution from untrusted sources.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
I flagged git clone + install commands that fetch and then execute remote code from the repositories https://github.com/NVlabs/cosmos-policy.git and https://github.com/moojink/robocasa-cosmos-policy.git because the skill runtime instructs cloning and installing those repos (git clone + uv pip install / python -m), meaning remote code is fetched and executed as a required dependency.
- Repository
- Orchestra-Research/AI-Research-SKILLs
- Commit
773a529
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.