Trust Assessment
healthcheck received a trust score of 95/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Broad read-only system information gathering with single approval.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 18, 2026 (commit b62bd290). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Broad read-only system information gathering with single approval The skill instructs the agent to request a single permission from the user to run 'read-only checks.' If granted, the agent proceeds to execute a wide array of system commands (`ss`, `lsof`, firewall status commands, `tmutil status`, `openclaw security audit --deep`) that gather extensive and potentially sensitive information about the host's operating system, network configuration, running processes, backup status, and OpenClaw's security posture. While these actions are read-only, granting such broad access with a single approval could expose a significant amount of system state. The rubric's instructions for redaction apply to *memory writes*, but not explicitly to the raw output processed by the LLM or displayed to the user before redaction, potentially leading to sensitive data exposure during processing or display. Consider breaking down the 'read-only checks' into more granular categories requiring separate approvals, especially for commands that reveal sensitive network or process information. Explicitly state that *all* output from these commands should be processed with redaction in mind before being transmitted to the LLM or stored, not just for memory writes or final summaries. | LLM | SKILL.md:48 |
Scan History
Embed Code
[](https://skillshield.io/report/cb4e7ebcb9b64383)
Powered by SkillShield