ClawHub

Periodic Reflection

Security checks across malware telemetry and agentic risk

Overview

This skill is local and not destructive, but its scheduled auto mode can repeatedly generate reports using hardcoded healthy metrics instead of real monitoring data.

Install only if you treat this as a report template, not a real monitoring system. Do not enable the cron job until the hardcoded metrics are replaced with verified data collection, and keep generated reports in a dedicated reports directory so output writes are easy to review.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger conditions are broad and ambiguous, including generic terms like '反思', '复盘', and '周期性总结', which can cause the skill to activate in contexts the user did not intend. Over-broad activation increases the chance of inappropriate skill selection, context hijacking, and unintended workflow execution, especially when the skill encourages automation and scheduled reporting.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill description is written to operate in Chinese without indicating language negotiation or respecting the user's preferred language. This can cause the agent to switch languages unexpectedly, degrading usability and potentially causing misunderstanding in operational or analytical contexts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal