Back to skill

Security audit

subclip-native-video-workflows

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the scanners reported no security findings and rated the assessed behaviors as aligned with the skill, though one local reference was missing and coverage was marked partial.

The scan supports installing with the benign verdict, but it is not a guarantee of safety. Coverage was marked partial because one local reference could not be matched to a bundled artifact; consider whether that missing reference matters to you before installing.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep