ClawHub
Skill flagged — suspicious patterns detected

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

OpenClaw Debug

v1.0.0

When users encounter OpenClaw-related issues or errors, search official docs and GitHub issues first, then provide solutions. Use for: feature malfunctions,...

⭐ 0· 413·0 current·0 all-time
bySky Yan@skyan
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
Name and description (OpenClaw troubleshooting) match the SKILL.md workflow: ask for version/context, search docs (docs.openclaw.ai) and GitHub issues, and provide diagnosis and remediation. There are no unexpected credential or binary requirements.
✓
Instruction Scope
Runtime instructions stay on task: confirm version/platform/symptoms, search specified official URLs, analyze results, and produce a structured response. The doc suggests running `openclaw --version` as a user check, but does not require reading unrelated files or accessing secrets.
✓
Install Mechanism
No install spec and no code files — instruction-only skill. This is low risk and proportionate for a troubleshooting helper.
✓
Credentials
Requires no environment variables, credentials, or config paths. Nothing requests broad access to unrelated services or secrets.
✓
Persistence & Privilege
Skill is user-invocable and not always-enabled; autonomous invocation remains platform-default but the skill does not request persistent privileges or modify other skills. The guidance to 'record and follow up' is a usage recommendation, not an instruction to change agent/system config.
Assessment
This skill appears to do what it says: guide you through checking docs and GitHub and produce a remediation plan. It does not ask for credentials or install anything. Note that it may recommend running local checks such as `openclaw --version` — those require your explicit approval to execute or to provide output. If you want to limit autonomous actions, keep autonomous skill invocation off or review prompts before allowing local command execution.

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

latestvk974myj4v5bn4vpedzs0kc61h58210p4

License

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

Comments