ClawHub
Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

using-data-cli

v1.0.1

Use when the user wants to discover, track, sync, or query news, RSS, social, financial, or other external sources through agent-data-cli and any configured...

⭐ 1· 168·0 current·0 all-time
bySeverin Zhong@severinzhong
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description say this is a tooling wrapper for agent-data-cli to discover, sync, and query external sources. The SKILL.md exclusively documents CLI flows, workspace configuration, proxy settings, and safe command semantics that align with that purpose. No unrelated credentials, binaries, or config paths are requested.
✓
Instruction Scope
Runtime instructions focus on translating user intent into specific agent-data-cli commands and explicitly limit when remote side effects may occur (require explicit refs/verbs, avoid auto-subscribe). The doc tells the agent to run remote discovery, subscribe, update, query, or interact only when appropriate. It also documents proxy, workspace, and scheduling behavior — all relevant to operating the CLI. There are no instructions to read unrelated system files or exfiltrate data.
ℹ
Install Mechanism
This is an instruction-only skill and contains no embedded install spec, but the README suggests installing agent-data-cli by running commands that fetch code from external sources (git clone from GitHub and an npx skills add command). Pulling code from GitHub or running npx introduces the normal risks of executing third-party code; this is expected for installing a CLI but is something the operator should review before running.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md describes configuring proxies and a source_workspace, which are operational settings rather than secret requests. There are no demands for unrelated tokens or broad secrets.
✓
Persistence & Privilege
The skill does not request always:true and is user-invocable only; it does not ask to modify other skills or system-level agent configuration. It instructs optional scheduling via cron/systemd/launchd — which is normal for periodic syncs but requires user action and consent to create such entries.
Assessment
This skill is an instruction-only wrapper for the agent-data-cli tool and appears internally consistent. Before you follow the install steps, review the remote repository (https://github.com/severinzhong/agent-data-cli) yourself — cloning or running npx will fetch and execute third-party code. If you plan to enable periodic syncs (cron/systemd/launchd) or set proxy rules, run those jobs from a controlled host and ensure any credentials for external sources are only provided to trusted code. If you want maximum safety, run the CLI in an isolated environment (container or VM) and inspect the repo for unexpected network callbacks or credential-handling before enabling scheduled runs.

Like a lobster shell, security has layers — review code before you run it.

latestvk975zzvf0yq7kxnb764nbshrm5839qq4

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments