ClawHub

Miro board

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent for pushing workshop diagrams to Miro, but it can modify or delete live board content with too little confirmation.

Review before installing. Use a least-privileged Miro token limited to the intended board, inspect or clear _out/.state.json before first use, and require an explicit confirmation before apply or undo because reusing a sessionKey can replace or delete previously generated board items.

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 (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill declares DIRECT PUSH as the default when the user asks, which can cause immediate external side effects on a Miro board without a clearly separate confirmation step. In an agent setting, broad/default activation increases the chance of unintended invocation or accidental board modification from ambiguous user requests.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill instructs saving a generated JSON file to a local path but does not include an explicit user-facing notice that local files will be written. This can surprise users, create unintended persistence of potentially sensitive workshop data, and reduce transparency about local side effects.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill directs execution of a local script that applies changes to an external Miro board, creating real side effects without an explicit warning or confirmation step. Because it uses environment-provided credentials and modifies external state, accidental or prompt-induced execution could alter or overwrite shared board contents.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal