Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
tensorpool
v1.0.0This skill helps users migrate their local machine learning scripts to run on TensorPool GPU clusters using the interactive cluster workflow (tp ssh). Use th...
⭐ 0· 57·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The name/description (migrating local ML scripts to TensorPool via tp ssh) matches the instructions: discovering the tp CLI, creating clusters, transferring code, running on GPU, and debugging. There are no unrelated required env vars, binaries, or install steps declared.
Instruction Scope
SKILL.md tells the agent to 'proactively diagnose and fix the code without asking for permission' and to iterate until the script runs, including running pip installs, editing paths, creating directories, changing code (fixing dataloaders, dtypes, etc.), and re-running. That is scope creep from a user-consent perspective: it grants broad discretion to modify local code and environment automatically. The instructions also expect access to local files, SSH keys, and the user's TensorPool account — reasonable for the task but high-impact actions that should require explicit user approval and safe-guards.
Install Mechanism
This is an instruction-only skill with no install spec and no code files; nothing is written to disk by the skill itself. The runtime guidance to run 'pip install tensorpool' or pip install missing packages is expected for this purpose, but note these commands will alter the user's Python environment if executed.
Credentials
The skill declares no required environment variables or credentials. The instructions assume the user has a TensorPool account and local auth (tp CLI configured) and access to SSH keys, which is proportional. However, because the skill may prompt for or use API keys/SSH credentials at runtime, users should be aware the agent will operate using whatever local credentials or secrets they provide or that are present in the environment.
Persistence & Privilege
always is false and there's no install or self-persistence. The skill can be invoked autonomously (platform default), which increases impact if automated changes are allowed, but autonomy alone is not a disqualifier. The primary concern is the instruction to modify user files without explicit consent rather than persistent privileges.
What to consider before installing
This skill appears to do what it says (migrate scripts to TensorPool), but it instructs the agent to automatically edit, install packages, and re-run your code without asking. Before installing or enabling it: (1) require explicit confirmation before any changes, (2) use a disposable environment (virtualenv/conda or container) and back up your code, (3) be prepared to review all pip installs and code edits, (4) do not expose long-lived API keys/SSH keys unnecessarily — prefer temporary credentials or local authenticated sessions, and (5) monitor cluster creation to avoid unexpected cloud costs. If you need stronger guarantees, ask the skill author to remove the 'fix without asking' directive or to add an explicit opt-in prompt before making changes.Like a lobster shell, security has layers — review code before you run it.
latestvk97b7e45gqt5y1d0wc7m9g72c184685w
License
MIT-0
Free to use, modify, and redistribute. No attribution required.