Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Solo Impl
v1.3.0Autonomous executor for Solo CLI — actually runs setup, calibration, teleoperation, dataset recording, policy training, and inference commands in the user's...
⭐ 1· 43·0 current·0 all-time
bySamarth Shukla@samarthshukla6
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The name/description (autonomous executor for Solo CLI) matches the instructions and bundled domain actions: setup, calibration, teleop, recording, training, inference. Conditional env vars (HUGGINGFACE_TOKEN, WANDB_API_KEY) are relevant to push-to-hub and W&B logging. Minor metadata inconsistencies: skill.json version is 1.2.0 while registry lists 1.3.0, and the registry 'Source' is 'unknown' while installs/commands reference https://github.com/GetSoloTech/solo-cli and homepage points to GetSoloTech/Solo-claw — worth verifying upstream provenance.
Instruction Scope
SKILL.md gives detailed runtime instructions that intentionally run many shell commands (git clone, uv installer, pip installs, solo CLI commands) and open real terminal windows for interactive flows. That scope is appropriate for an executor skill, but it grants the agent broad ability to run system commands on your behalf — the skill includes transparency rules (must show commands and ask consent for the uv installer) which helps mitigate surprise.
Install Mechanism
This is an instruction-only skill (no install spec), but it instructs the agent to run a remote installer via curl -LsSf https://astral.sh/uv/install.sh | sh. Piping a remote script to sh is high-risk in general. The skill does disclose this and enforces an explicit consent step (Rule T1) before running it, which reduces but does not eliminate risk. Other installs are standard (git clone from GitHub, pip installs).
Credentials
Only conditional env vars are referenced (HUGGINGFACE_TOKEN and WANDB_API_KEY) and their intended use is documented. No unrelated credentials are requested. Note: the registry display showed 'Required env vars: [object Object], [object Object]' (likely a rendering bug); confirm the true declared variable names before trusting the UI.
Persistence & Privilege
always:false and default autonomous invocation behavior are appropriate for an executor skill. The skill does not request persistent system-wide privileges or modify other skills. It will open terminal popups and run processes (backgrounded or interactive) as described — this is expected behavior for a remote executor but increases the importance of reviewing commands before they run.
Assessment
This skill appears to do what it says (run Solo CLI flows) and only asks for conditional tokens for HuggingFace/W&B when you opt into those features. Before installing or using it: 1) Verify the skill's source (registry shows 'Source: unknown' and skill.json/version mismatch) and confirm you trust the referenced GitHub repositories. 2) Be cautious about the uv installer step: it pipes a remote script (https://astral.sh/uv/install.sh) to sh — only proceed if you trust astral.sh; consider installing uv yourself and answering 'no' to the consent prompt. 3) For pushes to HuggingFace or W&B, prefer scoped or temporary tokens and understand the skill will use whichever credentials are present. 4) When the skill prints the full command before opening a terminal, review it carefully (it will open terminals and run commands immediately after pre-flight). 5) If you have low tolerance for an agent executing system-level commands on your machine, do not enable autonomous invocation for this skill or run the steps manually instead.Like a lobster shell, security has layers — review code before you run it.
latestvk97dtdwf3va4x0ws4t3029fpd584kce1
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🦾 Clawdis
Env[object Object], [object Object]