Back to skill

Security audit

Wiro AI for Swift

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign because its reported external service connections fit its stated SDK purpose, with a note about an optional unpinned installation command; confidence is medium and the scan is partial.

Before installing, consider whether you trust the Wiro service connections and review the optional installation command and skill source. The verdict is benign, but confidence is medium: Skillspector marked its analysis partial because some local references 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
  • 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 (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

import WiroKit

let client = try WiroClient( proxyURL: URL(string: "https://api.example.com/wiro/v1")!, headers: ["Authorization": "Bearer (sessionToken)"] // your app's own user session )

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

)

text

- Each REST call goes to `proxyURL` plus the API path the SDK would call on Wiro (such as `/Run/{owner}/{project}`, `/Task/Detail` or `/File/Upload`). The backend forwards it to `https://api.wiro.ai/v1` and adds the project credentials (headers in https://wiro.ai/docs/authentication).
- Task WebSocket tracking still connects directly to Wiro, using a per-task token instead of a key.

The API key modes are for local development and the example app:

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The optional installation command uses npx skills without pinning the executable package version or the source repository revision. If followed, it can execute a changed or compromised package and install changed skill instructions; however, it is a documentation cross-reference rather than an automatic execution step, and the finding incorrectly describes the command as an MCP server.

Content

No source excerpt is available for this finding.