Back to skill

Security audit

timeBuzzer

Security checks for vulnerabilities and agentic risk

Overview

The timeBuzzer operations have clear safeguards, but setup can execute unverified downloaded code without separate approval.

Review and install a verified CLI separately before using the skill. Check or disable automatic skill synchronization, understand that OOMOL handles the connected account and requests, and retain the required confirmations for changes. The remote installers and hosted implementation were not verified; no malicious behavior was established.

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
98% confidence
Finding

The supplied code performs remote script execution rather than timeBuzzer operations. Nothing in the chunk establishes that the Oomol installer is a supporting dependency for the declared functionality. The downloaded script is not provided, so its subsequent actions cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS response directly into bash executes mutable remote content without an artifact integrity check or an opportunity to review it. The domain is a relevant dependency provider, not evidence of malicious intent, but compromise of its delivery infrastructure could lead to local file access, credential theft, or other actions under the executing account; this overlaps with SQP-2 rather than representing a separate attack path.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

First-time setup executes downloaded installation scripts without warning the user about remote code execution and local system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The setup instructions direct the agent to execute remotely downloaded shell or PowerShell code without requiring approval for local installation or verifying the downloaded artifact. Although restricted to a missing-CLI error, this allows a timeBuzzer data request to trigger arbitrary code execution with the agent process's permissions if the installer source is compromised.

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 83)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