Back to skill

Security audit

Ticket Tailor

Security checks for vulnerabilities and agentic risk

Overview

The Ticket Tailor features fit the stated purpose, but setup directs the agent to execute unverified remote installers without a clear user-approval step.

Review the setup before installing. Prefer a separately verified CLI release and require approval before running downloaded installers. Review the CLI's automatic skill synchronization and authorize only the Ticket Tailor data access you need through OOMOL. Remote installer contents and hosted connector implementation remain unverified; the reviewed artifact shows no malicious intent.

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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command executes a remote installation script and contains no Ticket Tailor operations. Nothing in the provided code establishes that this installation supports the declared Ticket Tailor functionality. The downloaded script's contents and resulting system changes cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

Authentication could support a Ticket Tailor integration, but the supplied chunk consists solely of a login command and establishes no connection to Ticket Tailor. As supplied, its primary behavior differs materially from the declared search-and-read purpose.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a live network response directly into Bash without pinning an artifact or verifying its integrity; the PowerShell alternative uses the same download-and-execute pattern. Compromise of the distribution endpoint could execute arbitrary code with the agent's local privileges, exposing files and credentials, although the endpoint's role as the actual CLI provider makes malicious author intent less likely.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

The setup workflow instructs the agent to execute downloaded installer scripts without warning the user about running remote code and modifying their system.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

A missing CLI causes the workflow to direct installation without requiring informed user approval for executing remote code or modifying the local system. The conditional setup context limits exposure, but authorization to read Ticket Tailor data does not inherently authorize installing software.

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 81)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