Back to skill

Security audit

Wiro AI Text to Speech

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners found no reported executable code or major security issues, but flagged a possible privacy disclosure gap when text is sent to an external speech-generation service.

Before using it, consider whether the text you provide may be sent to Wiro AI for speech generation, and avoid including confidential or sensitive material unless you are authorized to share it. The scan was partial because a referenced path could not be resolved, so the evidence is incomplete.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow submits user text to an external speech-generation service without a privacy disclosure.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The workflow instructs the agent to call run_model with the user's text, which may include contents read from a project file under line L10. Although it discloses costs, it does not warn that this text will be transmitted to Wiro AI for processing.

Content

No source excerpt is available for this finding.