Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
- Without declared permissions the skill's intent is opaque and cannot be validated.
Security checks across malware telemetry and agentic risk
This is a disclosed local cron-health reporting skill that reads OpenClaw cron job history and does not show hidden network, write, or destructive behavior.
Before installing, confirm the publisher and naming mismatch are acceptable. Use the scheduled cron example only if you want recurring agent-based monitoring, and avoid sharing outputs if job names or error logs may contain secrets, tokens, or private operational details.
65/65 vendors flagged this skill as clean.