Back to skill

Security audit

VectorShift

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for operating VectorShift through OOMOL, but its setup instructions include running a remotely downloaded installer directly in a shell.

Review the oo CLI installer source or install the CLI through a trusted package manager or official manual process before using this skill. Once installed and connected, the normal VectorShift operations are scoped through the oo connector and include confirmation guidance for state-changing actions.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Script Fetching

High
Category
Supply Chain
Confidence
91% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This creates a supply-chain and remote-code-execution risk because any compromise of the download host, transport, or script content leads to immediate execution of attacker-controlled code on the local system without verification.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Static analysis

No suspicious patterns detected.