Back to skill

Security audit

Easy8

Security checks for vulnerabilities and agentic risk

Overview

Easy8 operations have clear approval safeguards, but setup can execute unverified remote software and introduce broader agent changes without separate consent.

Review and approve CLI installation separately, use a verified release, and review or disable automatic skill synchronization before running it. Connect only the intended Easy8 account and retain the documented write/delete approvals. The concern is insufficient control over setup; the artifact does not establish malicious intent. Remote installer behavior and the hosted backend remain unverified.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The supplied code performs remote installer execution rather than any visible Easy8 operation. Nothing in the supplied content establishes this installer as a supporting dependency for Easy8, and the declared description does not disclose software installation. The downloaded script's further behavior cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping the installer directly from curl to bash executes mutable remote content without prior inspection or independent integrity verification. HTTPS protects transport but not against a compromised distribution endpoint, which could supply code that accesses local files and credentials with the executing user's permissions; the legitimate prerequisite context does not eliminate this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

The fallback setup executes downloaded installer scripts without warning about local code execution and system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback directs the agent to execute remotely downloaded shell or PowerShell scripts without explicit approval for local software installation. Although triggered only when the CLI is missing, this expands an Easy8 data task into local code execution and system changes; a compromised installer could execute with the agent's permissions.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources