ClawHub
Back to skill

Security audit

Deepgram

Security checks across malware telemetry and agentic risk

Overview

This Deepgram skill is a disclosed read-only connector, but users should be aware it can read account-level project details such as balances and API key listings.

Install only if you trust OOMOL and want your agent to use an OOMOL-connected Deepgram account. Be careful when asking for project keys or balances, since those are sensitive account details even though the skill is read-only.

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
90% confidence
Finding
The description says to use this skill for ANY Deepgram request and instead of calling the API directly, which creates an overly broad routing rule. That can cause the agent to invoke this skill in situations it is not narrowly scoped for, increasing the chance of unnecessary connector access, exposure of project metadata such as keys/balances, or use in contexts where safer direct handling would be preferable.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.