Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Claw-SysInsight
v1.0.1Lightweight diagnostic tool for OpenClaw Agent to monitor OS resources, audit environment, and test network connectivity ensuring AI stability.
⭐ 0· 61·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The skill advertises deep resource tracking and environment auditing. However, the Python implementation returns simulated CPU and memory results (hardcoded 'optimal' values) rather than performing real measurements, which misaligns with the claimed capabilities. Network diagnostics are plausible for this purpose, but the code posts a JSON payload to a hardcoded webhook.site URL (an external third-party endpoint) which is not necessary for a local connectivity test and is disproportionate to the stated purpose.
Instruction Scope
SKILL.md emphasizes that all hardware diagnostics are processed locally and that it does not read sensitive files. That is contradicted by SysInsight.py's verify_network_connectivity function, which sends identifying JSON to an external webhook (Outbound HTTP POST). The SKILL.md even includes a comment instructing the user to 'replace with your webhook.site URL', which encourages providing/using external endpoints — this is outside the benign, local-scope behavior described and expands the data-surface to third parties.
Install Mechanism
No install spec is present and the skill is instruction-only with a single Python file. There is nothing being downloaded or written to disk by an installer in the manifest, which is low risk from an install mechanism perspective.
Credentials
The skill requests no environment variables or credentials, and the code does not read env vars or config paths. However, it does make an outbound network call that transmits a JSON payload (diagnostic_id, module name, timestamp). While no secrets are requested, outbound transmission to a third-party endpoint is a privacy/exfiltration risk and is not justified by the SKILL.md's 'local processing' claim.
Persistence & Privilege
The skill is not set to always: true, does not modify other skills or system configuration, and does not request persistent privileges. Autonomous invocation is allowed by default but is not combined with broad system access in this package.
What to consider before installing
Do not install this skill as-is. The code contradicts the README: it sends a JSON payload to a hardcoded webhook.site URL and uses simulated (fake) CPU/memory results rather than performing real diagnostics. This creates a data-leak risk (outbound HTTP to a third-party) and misleading behavior. If you need diagnostics: (1) refuse to install until the external-post behavior is removed or replaced with safe, auditable connectivity tests; (2) if you must test, run the skill only in an isolated VM/container with monitored network egress; (3) review and edit SysInsight.py to remove or change verify_network_connectivity so it performs local checks (e.g., use ICMP/ping or socket connect to specified hosts without sending identifying payloads) or point the endpoint to an internal, trusted server you control; (4) prefer a tool that actually samples system metrics (psutil, /proc) rather than returning hardcoded values. Because the source owner is unknown and the registry slug indicates 'deprecated-please-do-not-use', exercise extra caution.Like a lobster shell, security has layers — review code before you run it.
latestvk97dcp4tem95jjvv5r0ztwcr7h83mmav
License
MIT-0
Free to use, modify, and redistribute. No attribution required.