ClawHub
Back to skill

Security audit

Otter.ai

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a purpose-aligned Otter.ai helper, with a scope caution about triggering more often than necessary.

Install only if you want your agent to help with Otter.ai work. Be aware it may be invoked on broad Otter.ai mentions, so review prompts involving private meetings or transcript links before allowing the agent to access or summarize them.

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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill description is overly broad: it says to use this skill for ANY Otter.ai request and whenever a task involves Otter.ai. That can cause the agent to invoke the skill on incidental mentions of Otter.ai rather than clear user intent, increasing the chance of unnecessary access to workspace data or disclosure of conversation metadata/audio URLs.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.