ClawHub
Back to skill

Security audit

StackAI

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for operating StackAI through OOMOL, but its fallback setup tells agents to execute remote installer scripts without verification or explicit user approval.

Review the setup commands before installing. Prefer installing the oo CLI from official documentation with pinned releases or verification steps, and only let the skill run StackAI actions after you have intentionally installed and authenticated the CLI.

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
  • 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
95% 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 hosting domain, transport path, or install script would result in arbitrary command execution on the user's system without prior inspection. In a skill context, this is more dangerous because the content is guidance for an automated agent, increasing the chance of unquestioned execution during fallback handling.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Static analysis

No suspicious patterns detected.