ClawHub

Problem Solver

Security checks across malware telemetry and agentic risk

Overview

This is a local problem-solving helper that saves problem history on the user's machine, with no evidence of hidden network access or destructive behavior.

Install only if you are comfortable with problem descriptions, solutions, and progress notes being saved locally under ~/.openclaw/problem-solver/. Avoid entering passwords, secrets, or highly confidential personal, business, medical, or legal details, and delete the local folder if you do not want retained history.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

High
Confidence
96% confidence
Finding
The skill description advertises activation on very broad phrases like 'fix', 'help me decide', 'should I', and 'plan', which are common in normal conversation and not tightly scoped to explicit user intent to invoke this skill. Over-broad routing can cause the skill to activate unexpectedly and gain access to read/write-backed persistence during unrelated conversations, increasing privacy and safety risk.

Vague Triggers

High
Confidence
98% confidence
Finding
The documented activation list includes ambiguous single-word triggers such as 'solve', 'fix', 'debug', 'compare', 'plan', and phrases like 'why is', which can match many benign user messages not intended for this skill. In a skill with persistence features, accidental activation can lead to unintended collection, storage, and shaping of sensitive conversations.

Ssd 3

Medium
Confidence
97% confidence
Finding
The skill explicitly says to auto-log every problem solved to history.json in plain language, which is a data retention risk because users may disclose health, financial, employment, relationship, or other sensitive information while seeking help. Persistent natural-language logs create a durable privacy exposure even without network exfiltration.

Ssd 3

Medium
Confidence
95% confidence
Finding
The behavior rules, saved solutions, revisit flows, and stats features collectively encourage ongoing retention of user issues over time, which can accumulate sensitive personal and technical data beyond what is needed for the immediate interaction. This broad persistence model increases the harm from local compromise, accidental disclosure, or later unintended access.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal