Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
t
v1.0.0Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express...
⭐ 0· 158·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name/description and the runtime instructions consistently describe a 'find and install skills' helper that uses the Skills CLI (npx skills). There are no unrelated required env vars, binaries, or config paths.
Instruction Scope
The SKILL.md directs the agent to run npx skills find/add commands and to install skills with 'npx skills add <owner/repo@skill> -g -y'. That instructs fetching and executing third‑party code and explicitly recommends skipping user confirmation (-y) and installing globally (-g). While these steps are functionally required for installing skills, recommending bypassing prompts and global installs broadens the scope and risk of actions the agent will take.
Install Mechanism
This is an instruction-only skill (no install spec). It relies on npx to fetch packages from public registries/GitHub, which is a common but moderate-risk mechanism because it executes remote code. The SKILL.md points to skills.sh (a central index) — that is expected and preferable to arbitrary personal URLs.
Credentials
The skill requests no environment variables, credentials, or config paths. However, the recommended global installs (-g) will modify the user's environment, which is an expected but impactful side effect of the skill's purpose.
Persistence & Privilege
The skill is not marked 'always: true', but platform defaults allow autonomous invocation (disable-model-invocation: false). Combined with explicit instructions to run 'npx skills add ... -g -y', an autonomously invoked agent could install arbitrary third‑party code without additional user confirmation. That increases blast radius and warrants caution.
What to consider before installing
This skill is coherent — it helps find and install other skills — but it instructs the agent to fetch and install third‑party code (via npx) and even recommends skipping confirmations and installing globally. Before enabling or letting the agent run this skill autonomously: 1) Prefer manual review of search results and the target skill's GitHub page on skills.sh before installing. 2) Avoid using the '-y' flag or global installs; require explicit user confirmation for any 'npx skills add' operation. 3) If you must allow automated installs, restrict the agent's permission to run shell commands or require a second explicit user approval. 4) Verify the publisher and repository of any skill you install to reduce supply‑chain risk.Like a lobster shell, security has layers — review code before you run it.
latestvk97dc04jfs5qvjg8rpmakmgwsd837ej7
License
MIT-0
Free to use, modify, and redistribute. No attribution required.