Back to skill

Security audit

Cast

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Typecast text-to-speech helper, with the main caution that text may be sent to Typecast and credentials may be stored locally if the user logs in.

Install this only if you are comfortable using Typecast's cloud TTS service. Do not synthesize secrets, credentials, regulated data, or private text unless Typecast's data handling is acceptable to you; use logout or remove ~/.typecast/config.yaml if you no longer want credentials stored locally.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill invokes a cloud-backed TTS service and explicitly requires an API key, but the description does not warn users that provided text may be transmitted to a remote provider. Users may input sensitive prompts, secrets, or private content under the assumption processing is local, causing unintended data disclosure to a third party.

Static analysis

No suspicious patterns detected.