ClawHub

openclaw-reportstudio-community

Security checks across malware telemetry and agentic risk

Overview

This skill transparently runs a local reporting tool on user-selected spreadsheet files and writes report outputs, with no evidence of hidden network access, credential use, persistence, or destructive behavior.

Install only if you trust the local ReportStudio Python package it will run. Prefer the provided wrapper or structured command arguments, quote paths and column names, keep inputs and outputs in intended directories, and review generated warnings before sharing reports.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill invokes shell commands (`python -m reportstudio.cli.main`) and accepts a user-supplied file path and prompt, but it declares no explicit permissions or execution constraints. This creates a real security issue because the runtime can execute local code paths and process attacker-controlled inputs without a clear permission boundary, increasing the risk of command misuse, unintended file access, or unsafe downstream behavior.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger conditions are broad and based on open-ended natural language, causing the skill to activate for loosely related requests involving spreadsheets, reports, or exports. That ambiguity is dangerous because it can lead to unintended invocation on sensitive files or in contexts where the user did not clearly consent to local file processing and artifact generation.

VirusTotal

53/53 vendors flagged this skill as clean.

View on VirusTotal