ClawHub
Back to skill

Security audit

Transistor FM

Security checks across malware telemetry and agentic risk

Overview

This Transistor.fm skill appears legitimate, but it can publish, delete, or change podcast content and subscribers without documented confirmation safeguards.

Install only if you want an agent to operate your Transistor.fm account. Before any publish, schedule, delete, subscriber change, or file upload, require the agent to restate the show, episode or subscriber target, requested action, file path, and expected public/account impact, then wait for explicit confirmation.

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
93% confidence
Finding
The trigger description is broad enough to activate on many general podcast-management requests, which can cause the agent to route users into this skill even when they did not explicitly intend to perform Transistor.fm API actions. In a skill that can create, publish, update, and delete content, over-broad invocation increases the chance of unintended sensitive or destructive operations.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The stated purpose includes destructive operations such as deleting episodes or managing subscribers, but the documentation does not require confirmation, preview, or rollback guidance. In a production podcast platform, this creates a real risk of accidental data loss, subscriber impact, or unauthorized changes through ambiguous prompts.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The examples demonstrate how to publish or schedule episodes live without any warning that these actions affect public-facing content. While the API usage itself is legitimate, omitting a caution or confirmation step makes accidental publication more likely in an automated agent context.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.