Back to skill

Security audit

Eventzilla

Security checks for vulnerabilities and agentic risk

Overview

The Eventzilla lookups fit the stated purpose, but setup directs the agent to execute unverified remote installers without a separate approval step.

Review the setup before installing. Approve software installation separately, use a verified CLI release, and review or disable automatic skill synchronization. Expect authorized Eventzilla records to pass through OOMOL. The external installers and installed binary were not verified; the inspected artifact does not establish malicious intent or exfiltration.

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
99% confidence
Finding

The supplied command performs remote installer execution, not Eventzilla data retrieval. Nothing in the supplied chunk establishes this installation as a supporting dependency for Eventzilla access. The installer's contents are not provided, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The curl-to-bash command immediately executes mutable remote content without version pinning, signature verification, or an opportunity to inspect it. Compromise of the installer distribution path could execute arbitrary code with the invoking process's permissions, potentially exposing local credentials and files; HTTPS alone does not establish installer integrity. The PowerShell fallback has the same underlying risk.

Content

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

Fallback installation executes remote scripts without warning the user about the system-integrity risk.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

A missing CLI triggers instructions to install software by executing a remote script, without first explaining the system changes or requesting explicit approval. This expands a read-only Eventzilla task into local code execution with the agent's operating-system permissions; the conditional fallback reduces exposure but does not remove the risk.

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