ClawHub
Back to skill

Security audit

Manager Self Evolution

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed self-diagnosis helper that reads local OpenClaw memory/skill files and writes an evolution log, with no evidence of hidden execution, exfiltration, or destructive behavior.

Install this only if you want an agent to inspect its own local memory, principles, recent notes, and installed skills, and to keep a local evolution log. If you do not want routine self-auditing or Chinese-only output, keep it manual or avoid enabling the broad heartbeat/daily/task-before triggers.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger table uses broad conditions like '每次 heartbeat', '任何任务前', and '发现重大失误后' without defining scope, exclusions, or negative examples. These phrases could cause the skill to run in many ordinary contexts and make it unclear when activation should or should not occur.

Natural-Language Policy Violations

Medium
Confidence
86% confidence
Finding
The title and content are written in Chinese and do not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale constraint is documented and justified.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
This code file contains user-facing natural-language strings entirely in Chinese, including the title/description and runtime usage/output messages. Under the policy rule, forcing a specific language without offering a user choice or documenting a justified locale constraint is a natural-language policy violation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.