Skill flagged — suspicious patterns detected

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

Silviu Core

v1.0.0

Implements Silviu-specific guards and runbooks to enforce validation, prevent common errors, and manage browser and GitHub interactions in OpenClaw.

0· 365·0 current·0 all-time
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (browser + GitHub guardrails and runbooks) match the SKILL.md and included runbook files. All required actions (openclaw browser commands, curl github.com, git ls-remote, setting GIT_TERMINAL_PROMPT) are directly relevant to the described purpose.
Instruction Scope
SKILL.md only instructs checking browser relay status and performing harmless GitHub connectivity/preflight checks. It does not direct reading unrelated files, accessing credentials, or posting data to external endpoints beyond github.com (which is expected). The single environment change (export GIT_TERMINAL_PROMPT=0) is scoped to preventing interactive git prompts.
Install Mechanism
No install specification and no code files — instruction-only skill. Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no required environment variables or credentials. The one recommended export (GIT_TERMINAL_PROMPT=0) is appropriate for non-interactive git use and proportionate to performing repo preflight checks.
Persistence & Privilege
always is false and there are no instructions to modify agent/system-wide configuration or other skills. The skill does not request persistent presence or elevated privileges.
Assessment
This is an instruction-only runbook bundle that appears coherent and low-risk: it checks browser relay status and performs harmless GitHub preflight commands (curl to github.com, git ls-remote) and suggests exporting GIT_TERMINAL_PROMPT to avoid interactive prompts. Before enabling, confirm you trust the unknown publisher; although the runbooks are small and transparent, instruction-only skills execute shell commands and will make network requests (to github.com) and run git operations, which are visible in logs and to network monitoring. If you have stricter network or audit requirements, review the exact commands and run them manually first. No credentials are requested by the skill.

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

latestvk972348gfwr60pr8hkc434pnpx820kzv
365downloads
0stars
1versions
Updated 7h ago
v1.0.0
MIT-0

silviu-core

Silviu-specific ops guardrails and runbooks for OpenClaw.

What this skill does

  • Enforces: validate → execute → verify.
  • Prevents common failure modes:
    • No random package installs to solve unrelated tasks.
    • GitHub auth prompts are not treated as "network issues".
    • Browser automation requires an attached tab (Chrome relay ON).

Runbooks

Browser Attach Doctor

If openclaw browser tabs shows no tabs:

  1. Open Chrome
  2. Click OpenClaw Browser Relay on an active tab until it shows ON
  3. Re-run openclaw browser tabs

Repo Audit Preflight

Before cloning:

  • export GIT_TERMINAL_PROMPT=0
  • curl -I https://github.com
  • git ls-remote https://github.com/<owner>/<repo>.git | head

Comments

Loading comments...