ClawHub
Back to skill

Security audit

Podscribe

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only Podscribe connector guide with scoped use of the OOMOL CLI and no evidence of hidden or destructive behavior.

Install this if you want Codex to query Podscribe through an OOMOL-connected account. Be aware it may be selected broadly for Podscribe-related requests, and only complete the oo CLI install, login, or Podscribe connection steps when you intentionally want that account connected.

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
89% confidence
Finding
The manifest description says to use this skill for ANY Podscribe request and instead of calling the API directly, which is an overly broad routing trigger. Broad triggers can cause the agent to invoke this skill in situations where a narrower or safer tool would be more appropriate, increasing the chance of unintended command execution or overexposure of connected account data. In this context the available actions are read-only, which reduces severity, but the auto-invocation scope is still wider than necessary.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.