ClawHub
Back to skill

Security audit

wan

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent RunAPI/Wan media-generation helper, with expected network, authentication, upload, and download behavior for that purpose.

Install only if you are comfortable using RunAPI's CLI and sending prompts and any referenced media files to RunAPI/Wan. Generated deliverables are downloaded from URLs returned by the service, so handle them like untrusted media files and review any paid task before authorizing repeat submissions.

A.I.G

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

SkillSpector

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

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill explicitly instructs the agent to download arbitrary remote deliverable URLs with curl, but it does not require any user confirmation, domain allowlisting, or warning that executing the skill will retrieve external content over the network. In an agent setting, this can cause unexpected outbound requests to third-party URLs returned by the service, which increases SSRF-like exposure, privacy leakage, and retrieval of untrusted content even if the primary use case is legitimate media download.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.