ClawHub
Back to skill

Security audit

CastingWords

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly scoped CastingWords connector that discloses its read and submit actions and requires confirmation before writes.

Install this only if you intend to use OOMOL to access your CastingWords account. Review any submit_transcription payload carefully because it sends the provided media URL to CastingWords and may create a billable transcription job.

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 trigger text says to use this skill for ANY CastingWords request and instead of calling the API directly, which can cause the agent to invoke the skill for broadly scoped or ambiguous tasks without enough user-intent validation. Because the skill includes a write-capable action (`submit_transcription`), over-broad routing increases the chance of unintended state-changing operations or unnecessary exposure of user-supplied URLs to a third-party service.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.