Back to skill

Security audit

Wiro AI Model Search

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this skill benign with high confidence: they found no AIG issues and one low severity disclosure concern about sending request keywords to Wiro.

The scan supports installing the skill, but be aware that selected request keywords may be sent to Wiro. Avoid using sensitive or confidential details in queries if you install it.

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 sends keywords derived from the user's request to Wiro without a privacy disclosure.

Low
Category
Output Handling
Confidence
86% confidence
Finding

The skill instructs the agent to pass request-derived keywords to the remote Wiro recommendation service. Although the setup identifies the remote server, the description does not tell users that parts of their requests are transmitted to Wiro; the read-only assurance does not address this disclosure.

Content

No source excerpt is available for this finding.